RFC 6787
Media Resource Control Protocol Version 2 (MRCPv2)
15. ABNF Normative Definition
The following productions make use of the core rules defined in Section B.1 of RFC 5234 [RFC5234]. LWS = [*WSP CRLF] 1*WSP ; linear whitespace SWS = [LWS] ; sep whitespace UTF8-NONASCII = %xC0-DF 1UTF8-CONT / %xE0-EF 2UTF8-CONT / %xF0-F7 3UTF8-CONT / %xF8-FB 4UTF8-CONT / %xFC-FD 5UTF8-CONT UTF8-CONT = %x80-BF UTFCHAR = %x21-7E / UTF8-NONASCII param = *pchar
quoted-string = SWS DQUOTE *(qdtext / quoted-pair )
DQUOTE
qdtext = LWS / %x21 / %x23-5B / %x5D-7E
/ UTF8-NONASCII
quoted-pair = "\" (%x00-09 / %x0B-0C / %x0E-7F)
token = 1*(alphanum / "-" / "." / "!" / "%" / "*"
/ "_" / "+" / "`" / "'" / "~" )
reserved = ";" / "/" / "?" / ":" / "@" / "&" / "="
/ "+" / "$" / ","
mark = "-" / "_" / "." / "!" / "~" / "*" / "'"
/ "(" / ")"
unreserved = alphanum / mark
pchar = unreserved / escaped
/ ":" / "@" / "&" / "=" / "+" / "$" / ","
alphanum = ALPHA / DIGIT
BOOLEAN = "true" / "false"
FLOAT = *DIGIT ["." *DIGIT]
escaped = "%" HEXDIG HEXDIG
fragment = *uric
uri = [ absoluteURI / relativeURI ]
[ "#" fragment ]
absoluteURI = scheme ":" ( hier-part / opaque-part )
relativeURI = ( net-path / abs-path / rel-path )
[ "?" query ]
hier-part = ( net-path / abs-path ) [ "?" query ]
net-path = "//" authority [ abs-path ]
abs-path = "/" path-segments
rel-path = rel-segment [ abs-path ]
rel-segment = 1*( unreserved / escaped / ";" / "@"
/ "&" / "=" / "+" / "$" / "," )
opaque-part = uric-no-slash *uric
uric = reserved / unreserved / escaped
uric-no-slash = unreserved / escaped / ";" / "?" / ":"
/ "@" / "&" / "=" / "+" / "$" / ","
path-segments = segment *( "/" segment )
segment = *pchar *( ";" param )
scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
authority = srvr / reg-name
srvr = [ [ userinfo "@" ] hostport ]
reg-name = 1*( unreserved / escaped / "$" / ","
/ ";" / ":" / "@" / "&" / "=" / "+" )
query = *uric
userinfo = ( user ) [ ":" password ] "@"
user = 1*( unreserved / escaped
/ user-unreserved )
user-unreserved = "&" / "=" / "+" / "$" / "," / ";"
/ "?" / "/"
password = *( unreserved / escaped
/ "&" / "=" / "+" / "$" / "," )
hostport = host [ ":" port ]
host = hostname / IPv4address / IPv6reference
hostname = *( domainlabel "." ) toplabel [ "." ]
domainlabel = alphanum / alphanum *( alphanum / "-" )
alphanum
toplabel = ALPHA / ALPHA *( alphanum / "-" )
alphanum
IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "."
1*3DIGIT
IPv6reference = "[" IPv6address "]"
IPv6address = hexpart [ ":" IPv4address ]
hexpart = hexseq / hexseq "::" [ hexseq ] / "::"
[ hexseq ]
hexseq = hex4 *( ":" hex4)
hex4 = 1*4HEXDIG
port = 1*19DIGIT
; generic-message is the top-level rule
generic-message = start-line message-header CRLF
[ message-body ]
message-body = *OCTET
start-line = request-line / response-line / event-line
request-line = mrcp-version SP message-length SP method-name
SP request-id CRLF
response-line = mrcp-version SP message-length SP request-id
SP status-code SP request-state CRLF
event-line = mrcp-version SP message-length SP event-name
SP request-id SP request-state CRLF
method-name = generic-method
/ synthesizer-method
/ recognizer-method
/ recorder-method
/ verifier-method
generic-method = "SET-PARAMS"
/ "GET-PARAMS"
request-state = "COMPLETE"
/ "IN-PROGRESS"
/ "PENDING"
event-name = synthesizer-event
/ recognizer-event
/ recorder-event
/ verifier-event
message-header = 1*(generic-header / resource-header / generic-field)
generic-field = field-name ":" [ field-value ]
field-name = token
field-value = *LWS field-content *( CRLF 1*LWS field-content)
field-content = <the OCTETs making up the field-value
and consisting of either *TEXT or combinations
of token, separators, and quoted-string>
resource-header = synthesizer-header
/ recognizer-header
/ recorder-header
/ verifier-header
generic-header = channel-identifier
/ accept
/ active-request-id-list
/ proxy-sync-id
/ accept-charset
/ content-type
/ content-id
/ content-base
/ content-encoding
/ content-location
/ content-length
/ fetch-timeout
/ cache-control
/ logging-tag
/ set-cookie
/ vendor-specific
; -- content-id is as defined in RFC 2392, RFC 2046 and RFC 5322
; -- accept and accept-charset are as defined in RFC 2616
mrcp-version = "MRCP" "/" 1*2DIGIT "." 1*2DIGIT
message-length = 1*19DIGIT
request-id = 1*10DIGIT
status-code = 3DIGIT
channel-identifier = "Channel-Identifier" ":"
channel-id CRLF
channel-id = 1*alphanum "@" 1*alphanum
active-request-id-list = "Active-Request-Id-List" ":"
request-id *("," request-id) CRLF
proxy-sync-id = "Proxy-Sync-Id" ":" 1*VCHAR CRLF
content-base = "Content-Base" ":" absoluteURI CRLF
content-length = "Content-Length" ":" 1*19DIGIT CRLF
content-type = "Content-Type" ":" media-type-value CRLF
media-type-value = type "/" subtype *( ";" parameter )
type = token
subtype = token
parameter = attribute "=" value
attribute = token
value = token / quoted-string
content-encoding = "Content-Encoding" ":"
*WSP content-coding
*(*WSP "," *WSP content-coding *WSP )
CRLF
content-coding = token
content-location = "Content-Location" ":"
( absoluteURI / relativeURI ) CRLF
cache-control = "Cache-Control" ":"
[*WSP cache-directive
*( *WSP "," *WSP cache-directive *WSP )]
CRLF
fetch-timeout = "Fetch-Timeout" ":" 1*19DIGIT CRLF
cache-directive = "max-age" "=" delta-seconds
/ "max-stale" ["=" delta-seconds ]
/ "min-fresh" "=" delta-seconds
delta-seconds = 1*19DIGIT
logging-tag = "Logging-Tag" ":" 1*UTFCHAR CRLF
vendor-specific = "Vendor-Specific-Parameters" ":"
[vendor-specific-av-pair
*(";" vendor-specific-av-pair)] CRLF
vendor-specific-av-pair = vendor-av-pair-name "="
value
vendor-av-pair-name = 1*UTFCHAR
set-cookie = "Set-Cookie:" SP set-cookie-string
set-cookie-string = cookie-pair *( ";" SP cookie-av )
cookie-pair = cookie-name "=" cookie-value
cookie-name = token
cookie-value = *cookie-octet / ( DQUOTE *cookie-octet DQUOTE )
cookie-octet = %x21 / %x23-2B / %x2D-3A / %x3C-5B / %x5D-7E
token = <token, defined in [RFC2616], Section 2.2>
cookie-av = expires-av / max-age-av / domain-av /
path-av / secure-av / httponly-av /
extension-av / age-av
expires-av = "Expires=" sane-cookie-date
sane-cookie-date = <rfc1123-date, defined in [RFC2616], Section 3.3.1>
max-age-av = "Max-Age=" non-zero-digit *DIGIT
non-zero-digit = %x31-39
domain-av = "Domain=" domain-value
domain-value = <subdomain>
path-av = "Path=" path-value
path-value = <any CHAR except CTLs or ";">
secure-av = "Secure"
httponly-av = "HttpOnly"
extension-av = <any CHAR except CTLs or ";">
age-av = "Age=" delta-seconds
; Synthesizer ABNF
synthesizer-method = "SPEAK"
/ "STOP"
/ "PAUSE"
/ "RESUME"
/ "BARGE-IN-OCCURRED"
/ "CONTROL"
/ "DEFINE-LEXICON"
synthesizer-event = "SPEECH-MARKER"
/ "SPEAK-COMPLETE"
synthesizer-header = jump-size
/ kill-on-barge-in
/ speaker-profile
/ completion-cause
/ completion-reason
/ voice-parameter
/ prosody-parameter
/ speech-marker
/ speech-language
/ fetch-hint
/ audio-fetch-hint
/ failed-uri
/ failed-uri-cause
/ speak-restart
/ speak-length
/ load-lexicon
/ lexicon-search-order
jump-size = "Jump-Size" ":" speech-length-value CRLF
speech-length-value = numeric-speech-length
/ text-speech-length
text-speech-length = 1*UTFCHAR SP "Tag"
numeric-speech-length = ("+" / "-") positive-speech-length
positive-speech-length = 1*19DIGIT SP numeric-speech-unit
numeric-speech-unit = "Second"
/ "Word"
/ "Sentence"
/ "Paragraph"
kill-on-barge-in = "Kill-On-Barge-In" ":" BOOLEAN
CRLF
speaker-profile = "Speaker-Profile" ":" uri CRLF
completion-cause = "Completion-Cause" ":" cause-code SP
cause-name CRLF
cause-code = 3DIGIT
cause-name = *VCHAR
completion-reason = "Completion-Reason" ":"
quoted-string CRLF
voice-parameter = voice-gender
/ voice-age
/ voice-variant
/ voice-name
voice-gender = "Voice-Gender:" voice-gender-value CRLF
voice-gender-value = "male"
/ "female"
/ "neutral"
voice-age = "Voice-Age:" 1*3DIGIT CRLF
voice-variant = "Voice-Variant:" 1*19DIGIT CRLF
voice-name = "Voice-Name:"
1*UTFCHAR *(1*WSP 1*UTFCHAR) CRLF
prosody-parameter = "Prosody-" prosody-param-name ":"
prosody-param-value CRLF
prosody-param-name = 1*VCHAR
prosody-param-value = 1*VCHAR
timestamp = "timestamp" "=" time-stamp-value
time-stamp-value = 1*20DIGIT
speech-marker = "Speech-Marker" ":"
timestamp
[";" 1*(UTFCHAR / %x20)] CRLF
speech-language = "Speech-Language" ":" 1*VCHAR CRLF
fetch-hint = "Fetch-Hint" ":" ("prefetch" / "safe") CRLF
audio-fetch-hint = "Audio-Fetch-Hint" ":"
("prefetch" / "safe" / "stream") CRLF
failed-uri = "Failed-URI" ":" absoluteURI CRLF
failed-uri-cause = "Failed-URI-Cause" ":" 1*UTFCHAR CRLF
speak-restart = "Speak-Restart" ":" BOOLEAN CRLF
speak-length = "Speak-Length" ":" positive-length-value
CRLF
positive-length-value = positive-speech-length
/ text-speech-length
load-lexicon = "Load-Lexicon" ":" BOOLEAN CRLF
lexicon-search-order = "Lexicon-Search-Order" ":"
"<" absoluteURI ">" *(" " "<" absoluteURI ">") CRLF
; Recognizer ABNF
recognizer-method = recog-only-method
/ enrollment-method
recog-only-method = "DEFINE-GRAMMAR"
/ "RECOGNIZE"
/ "INTERPRET"
/ "GET-RESULT"
/ "START-INPUT-TIMERS"
/ "STOP"
enrollment-method = "START-PHRASE-ENROLLMENT"
/ "ENROLLMENT-ROLLBACK"
/ "END-PHRASE-ENROLLMENT"
/ "MODIFY-PHRASE"
/ "DELETE-PHRASE"
recognizer-event = "START-OF-INPUT"
/ "RECOGNITION-COMPLETE"
/ "INTERPRETATION-COMPLETE"
recognizer-header = recog-only-header
/ enrollment-header
recog-only-header = confidence-threshold
/ sensitivity-level
/ speed-vs-accuracy
/ n-best-list-length
/ input-type
/ no-input-timeout
/ recognition-timeout
/ waveform-uri
/ input-waveform-uri
/ completion-cause
/ completion-reason
/ recognizer-context-block
/ start-input-timers
/ speech-complete-timeout
/ speech-incomplete-timeout
/ dtmf-interdigit-timeout
/ dtmf-term-timeout
/ dtmf-term-char
/ failed-uri
/ failed-uri-cause
/ save-waveform
/ media-type
/ new-audio-channel
/ speech-language
/ ver-buffer-utterance
/ recognition-mode
/ cancel-if-queue
/ hotword-max-duration
/ hotword-min-duration
/ interpret-text
/ dtmf-buffer-time
/ clear-dtmf-buffer
/ early-no-match
enrollment-header = num-min-consistent-pronunciations
/ consistency-threshold
/ clash-threshold
/ personal-grammar-uri
/ enroll-utterance
/ phrase-id
/ phrase-nl
/ weight
/ save-best-waveform
/ new-phrase-id
/ confusable-phrases-uri
/ abort-phrase-enrollment
confidence-threshold = "Confidence-Threshold" ":"
FLOAT CRLF
sensitivity-level = "Sensitivity-Level" ":" FLOAT
CRLF
speed-vs-accuracy = "Speed-Vs-Accuracy" ":" FLOAT
CRLF
n-best-list-length = "N-Best-List-Length" ":" 1*19DIGIT
CRLF
input-type = "Input-Type" ":" inputs CRLF
inputs = "speech" / "dtmf"
no-input-timeout = "No-Input-Timeout" ":" 1*19DIGIT
CRLF
recognition-timeout = "Recognition-Timeout" ":" 1*19DIGIT
CRLF
waveform-uri = "Waveform-URI" ":" ["<" uri ">"
";" "size" "=" 1*19DIGIT
";" "duration" "=" 1*19DIGIT] CRLF
recognizer-context-block = "Recognizer-Context-Block" ":"
[1*VCHAR] CRLF
start-input-timers = "Start-Input-Timers" ":"
BOOLEAN CRLF
speech-complete-timeout = "Speech-Complete-Timeout" ":"
1*19DIGIT CRLF
speech-incomplete-timeout = "Speech-Incomplete-Timeout" ":"
1*19DIGIT CRLF
dtmf-interdigit-timeout = "DTMF-Interdigit-Timeout" ":"
1*19DIGIT CRLF
dtmf-term-timeout = "DTMF-Term-Timeout" ":" 1*19DIGIT
CRLF
dtmf-term-char = "DTMF-Term-Char" ":" VCHAR CRLF
save-waveform = "Save-Waveform" ":" BOOLEAN CRLF
new-audio-channel = "New-Audio-Channel" ":"
BOOLEAN CRLF
recognition-mode = "Recognition-Mode" ":"
"normal" / "hotword" CRLF
cancel-if-queue = "Cancel-If-Queue" ":" BOOLEAN CRLF
hotword-max-duration = "Hotword-Max-Duration" ":"
1*19DIGIT CRLF
hotword-min-duration = "Hotword-Min-Duration" ":"
1*19DIGIT CRLF
interpret-text = "Interpret-Text" ":" 1*VCHAR CRLF
dtmf-buffer-time = "DTMF-Buffer-Time" ":" 1*19DIGIT CRLF
clear-dtmf-buffer = "Clear-DTMF-Buffer" ":" BOOLEAN CRLF
early-no-match = "Early-No-Match" ":" BOOLEAN CRLF
num-min-consistent-pronunciations =
"Num-Min-Consistent-Pronunciations" ":" 1*19DIGIT CRLF
consistency-threshold = "Consistency-Threshold" ":" FLOAT
CRLF
clash-threshold = "Clash-Threshold" ":" FLOAT CRLF
personal-grammar-uri = "Personal-Grammar-URI" ":" uri CRLF
enroll-utterance = "Enroll-Utterance" ":" BOOLEAN CRLF
phrase-id = "Phrase-ID" ":" 1*VCHAR CRLF
phrase-nl = "Phrase-NL" ":" 1*UTFCHAR CRLF
weight = "Weight" ":" FLOAT CRLF
save-best-waveform = "Save-Best-Waveform" ":"
BOOLEAN CRLF
new-phrase-id = "New-Phrase-ID" ":" 1*VCHAR CRLF
confusable-phrases-uri = "Confusable-Phrases-URI" ":"
uri CRLF
abort-phrase-enrollment = "Abort-Phrase-Enrollment" ":"
BOOLEAN CRLF
; Recorder ABNF
recorder-method = "RECORD"
/ "STOP"
/ "START-INPUT-TIMERS"
recorder-event = "START-OF-INPUT"
/ "RECORD-COMPLETE"
recorder-header = sensitivity-level
/ no-input-timeout
/ completion-cause
/ completion-reason
/ failed-uri
/ failed-uri-cause
/ record-uri
/ media-type
/ max-time
/ trim-length
/ final-silence
/ capture-on-speech
/ ver-buffer-utterance
/ start-input-timers
/ new-audio-channel
record-uri = "Record-URI" ":" [ "<" uri ">"
";" "size" "=" 1*19DIGIT
";" "duration" "=" 1*19DIGIT] CRLF
media-type = "Media-Type" ":" media-type-value CRLF
max-time = "Max-Time" ":" 1*19DIGIT CRLF
trim-length = "Trim-Length" ":" 1*19DIGIT CRLF
final-silence = "Final-Silence" ":" 1*19DIGIT CRLF
capture-on-speech = "Capture-On-Speech " ":"
BOOLEAN CRLF
; Verifier ABNF
verifier-method = "START-SESSION"
/ "END-SESSION"
/ "QUERY-VOICEPRINT"
/ "DELETE-VOICEPRINT"
/ "VERIFY"
/ "VERIFY-FROM-BUFFER"
/ "VERIFY-ROLLBACK"
/ "STOP"
/ "CLEAR-BUFFER"
/ "START-INPUT-TIMERS"
/ "GET-INTERMEDIATE-RESULT"
verifier-event = "VERIFICATION-COMPLETE"
/ "START-OF-INPUT"
verifier-header = repository-uri
/ voiceprint-identifier
/ verification-mode
/ adapt-model
/ abort-model
/ min-verification-score
/ num-min-verification-phrases
/ num-max-verification-phrases
/ no-input-timeout
/ save-waveform
/ media-type
/ waveform-uri
/ voiceprint-exists
/ ver-buffer-utterance
/ input-waveform-uri
/ completion-cause
/ completion-reason
/ speech-complete-timeout
/ new-audio-channel
/ abort-verification
/ start-input-timers
/ input-type
repository-uri = "Repository-URI" ":" uri CRLF
voiceprint-identifier = "Voiceprint-Identifier" ":"
vid *[";" vid] CRLF
vid = 1*VCHAR ["." 1*VCHAR]
verification-mode = "Verification-Mode" ":"
verification-mode-string
verification-mode-string = "train" / "verify"
adapt-model = "Adapt-Model" ":" BOOLEAN CRLF
abort-model = "Abort-Model" ":" BOOLEAN CRLF
min-verification-score = "Min-Verification-Score" ":"
[ %x2D ] FLOAT CRLF
num-min-verification-phrases = "Num-Min-Verification-Phrases"
":" 1*19DIGIT CRLF
num-max-verification-phrases = "Num-Max-Verification-Phrases"
":" 1*19DIGIT CRLF
voiceprint-exists = "Voiceprint-Exists" ":"
BOOLEAN CRLF
ver-buffer-utterance = "Ver-Buffer-Utterance" ":"
BOOLEAN CRLF
input-waveform-uri = "Input-Waveform-URI" ":" uri CRLF
abort-verification = "Abort-Verification " ":"
BOOLEAN CRLF
The following productions add a new SDP session-level attribute. See
Paragraph 5.
cmid-attribute = "a=cmid:" identification-tag
identification-tag = token
16. XML Schemas
16.1. NLSML Schema Definition
<?xml version="1.0" encoding="UTF-8"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema"
targetNamespace="urn:ietf:params:xml:ns:mrcpv2"
xmlns="urn:ietf:params:xml:ns:mrcpv2"
elementFormDefault="qualified"
attributeFormDefault="unqualified" >
<xs:annotation>
<xs:documentation> Natural Language Semantic Markup Schema
</xs:documentation>
</xs:annotation>
<xs:include schemaLocation="enrollment-schema.rng"/>
<xs:include schemaLocation="verification-schema.rng"/>
<xs:element name="result">
<xs:complexType>
<xs:sequence>
<xs:element name="interpretation" maxOccurs="unbounded">
<xs:complexType>
<xs:sequence>
<xs:element name="instance">
<xs:complexType mixed="true">
<xs:sequence minOccurs="0">
<xs:any namespace="##other" processContents="lax"/>
</xs:sequence>
</xs:complexType>
</xs:element>
<xs:element name="input" minOccurs="0">
<xs:complexType mixed="true">
<xs:choice>
<xs:element name="noinput" minOccurs="0"/>
<xs:element name="nomatch" minOccurs="0"/>
<xs:element name="input" minOccurs="0"/>
</xs:choice>
<xs:attribute name="mode"
type="xs:string"
default="speech"/>
<xs:attribute name="confidence"
type="confidenceinfo"
default="1.0"/>
<xs:attribute name="timestamp-start"
type="xs:string"/>
<xs:attribute name="timestamp-end"
type="xs:string"/>
</xs:complexType>
</xs:element>
</xs:sequence>
<xs:attribute name="confidence" type="confidenceinfo"
default="1.0"/>
<xs:attribute name="grammar" type="xs:anyURI"
use="optional"/>
</xs:complexType>
</xs:element>
<xs:element name="enrollment-result"
type="enrollment-contents"/>
<xs:element name="verification-result"
type="verification-contents"/>
</xs:sequence>
<xs:attribute name="grammar" type="xs:anyURI"
use="optional"/>
</xs:complexType>
</xs:element>
<xs:simpleType name="confidenceinfo">
<xs:restriction base="xs:float">
<xs:minInclusive value="0.0"/>
<xs:maxInclusive value="1.0"/>
</xs:restriction>
</xs:simpleType>
</xs:schema>
16.2. Enrollment Results Schema Definition
<?xml version="1.0" encoding="UTF-8"?> <!-- MRCP Enrollment Schema (See http://www.oasis-open.org/committees/relax-ng/spec.html) --> <grammar datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes" ns="urn:ietf:params:xml:ns:mrcpv2" xmlns="http://relaxng.org/ns/structure/1.0"> <start> <element name="enrollment-result"> <ref name="enrollment-content"/> </element> </start> <define name="enrollment-content"> <interleave> <element name="num-clashes"> <data type="nonNegativeInteger"/> </element> <element name="num-good-repetitions"> <data type="nonNegativeInteger"/> </element> <element name="num-repetitions-still-needed"> <data type="nonNegativeInteger"/> </element> <element name="consistency-status"> <choice> <value>consistent</value> <value>inconsistent</value> <value>undecided</value> </choice> </element> <optional> <element name="clash-phrase-ids"> <oneOrMore> <element name="item"> <data type="token"/> </element> </oneOrMore> </element> </optional> <optional> <element name="transcriptions"> <oneOrMore>
<element name="item">
<text/>
</element>
</oneOrMore>
</element>
</optional>
<optional>
<element name="confusable-phrases">
<oneOrMore>
<element name="item">
<text/>
</element>
</oneOrMore>
</element>
</optional>
</interleave>
</define>
</grammar>
16.3. Verification Results Schema Definition
<?xml version="1.0" encoding="UTF-8"?>
<!-- MRCP Verification Results Schema
(See http://www.oasis-open.org/committees/relax-ng/spec.html)
-->
<grammar datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes"
ns="urn:ietf:params:xml:ns:mrcpv2"
xmlns="http://relaxng.org/ns/structure/1.0">
<start>
<element name="verification-result">
<ref name="verification-contents"/>
</element>
</start>
<define name="verification-contents">
<element name="voiceprint">
<ref name="firstVoiceprintContent"/>
</element>
<zeroOrMore>
<element name="voiceprint">
<ref name="restVoiceprintContent"/>
</element>
</zeroOrMore>
</define>
<define name="firstVoiceprintContent">
<attribute name="id">
<data type="string"/>
</attribute>
<interleave>
<optional>
<element name="adapted">
<data type="boolean"/>
</element>
</optional>
<optional>
<element name="needmoredata">
<ref name="needmoredataContent"/>
</element>
</optional>
<optional>
<element name="incremental">
<ref name="firstCommonContent"/>
</element>
</optional>
<element name="cumulative">
<ref name="firstCommonContent"/>
</element>
</interleave>
</define>
<define name="restVoiceprintContent">
<attribute name="id">
<data type="string"/>
</attribute>
<element name="cumulative">
<ref name="restCommonContent"/>
</element>
</define>
<define name="firstCommonContent">
<interleave>
<element name="decision">
<ref name="decisionContent"/>
</element>
<optional>
<element name="utterance-length">
<ref name="utterance-lengthContent"/>
</element>
</optional>
<optional>
<element name="device">
<ref name="deviceContent"/>
</element>
</optional>
<optional>
<element name="gender">
<ref name="genderContent"/>
</element>
</optional>
<zeroOrMore>
<element name="verification-score">
<ref name="verification-scoreContent"/>
</element>
</zeroOrMore>
</interleave>
</define>
<define name="restCommonContent">
<interleave>
<optional>
<element name="decision">
<ref name="decisionContent"/>
</element>
</optional>
<optional>
<element name="device">
<ref name="deviceContent"/>
</element>
</optional>
<optional>
<element name="gender">
<ref name="genderContent"/>
</element>
</optional>
<zeroOrMore>
<element name="verification-score">
<ref name="verification-scoreContent"/>
</element>
</zeroOrMore>
</interleave>
</define>
<define name="decisionContent">
<choice>
<value>accepted</value>
<value>rejected</value>
<value>undecided</value>
</choice>
</define>
<define name="needmoredataContent">
<data type="boolean"/>
</define>
<define name="utterance-lengthContent">
<data type="nonNegativeInteger"/>
</define>
<define name="deviceContent">
<choice>
<value>cellular-phone</value>
<value>electret-phone</value>
<value>carbon-button-phone</value>
<value>unknown</value>
</choice>
</define>
<define name="genderContent">
<choice>
<value>male</value>
<value>female</value>
<value>unknown</value>
</choice>
</define>
<define name="verification-scoreContent">
<data type="float">
<param name="minInclusive">-1</param>
<param name="maxInclusive">1</param>
</data>
</define>
</grammar>
17. References
17.1. Normative References
[ISO.8859-1.1987] International Organization for Standardization, "Information technology - 8-bit single byte coded graphic - character sets - Part 1: Latin alphabet No. 1, JTC1/ SC2", ISO Standard 8859-1, 1987. [RFC0793] Postel, J., "Transmission Control Protocol", STD 7, RFC 793, September 1981. [RFC1035] Mockapetris, P., "Domain names - implementation and specification", STD 13, RFC 1035, November 1987. [RFC2119] Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, March 1997. [RFC2326] Schulzrinne, H., Rao, A., and R. Lanphier, "Real Time Streaming Protocol (RTSP)", RFC 2326, April 1998. [RFC2392] Levinson, E., "Content-ID and Message-ID Uniform Resource Locators", RFC 2392, August 1998. [RFC2483] Mealling, M. and R. Daniel, "URI Resolution Services Necessary for URN Resolution", RFC 2483, January 1999. [RFC2616] Fielding, R., Gettys, J., Mogul, J., Frystyk, H., Masinter, L., Leach, P., and T. Berners-Lee, "Hypertext Transfer Protocol -- HTTP/1.1", RFC 2616, June 1999. [RFC3023] Murata, M., St. Laurent, S., and D. Kohn, "XML Media Types", RFC 3023, January 2001. [RFC3261] Rosenberg, J., Schulzrinne, H., Camarillo, G., Johnston, A., Peterson, J., Sparks, R., Handley, M., and E. Schooler, "SIP: Session Initiation Protocol", RFC 3261, June 2002. [RFC3264] Rosenberg, J. and H. Schulzrinne, "An Offer/Answer Model with Session Description Protocol (SDP)", RFC 3264, June 2002. [RFC3550] Schulzrinne, H., Casner, S., Frederick, R., and V. Jacobson, "RTP: A Transport Protocol for Real-Time Applications", STD 64, RFC 3550, July 2003.
[RFC3629] Yergeau, F., "UTF-8, a transformation format of ISO 10646", STD 63, RFC 3629, November 2003. [RFC3688] Mealling, M., "The IETF XML Registry", BCP 81, RFC 3688, January 2004. [RFC3711] Baugher, M., McGrew, D., Naslund, M., Carrara, E., and K. Norrman, "The Secure Real-time Transport Protocol (SRTP)", RFC 3711, March 2004. [RFC3986] Berners-Lee, T., Fielding, R., and L. Masinter, "Uniform Resource Identifier (URI): Generic Syntax", STD 66, RFC 3986, January 2005. [RFC4145] Yon, D. and G. Camarillo, "TCP-Based Media Transport in the Session Description Protocol (SDP)", RFC 4145, September 2005. [RFC4288] Freed, N. and J. Klensin, "Media Type Specifications and Registration Procedures", BCP 13, RFC 4288, December 2005. [RFC4566] Handley, M., Jacobson, V., and C. Perkins, "SDP: Session Description Protocol", RFC 4566, July 2006. [RFC4568] Andreasen, F., Baugher, M., and D. Wing, "Session Description Protocol (SDP) Security Descriptions for Media Streams", RFC 4568, July 2006. [RFC4572] Lennox, J., "Connection-Oriented Media Transport over the Transport Layer Security (TLS) Protocol in the Session Description Protocol (SDP)", RFC 4572, July 2006. [RFC5226] Narten, T. and H. Alvestrand, "Guidelines for Writing an IANA Considerations Section in RFCs", BCP 26, RFC 5226, May 2008. [RFC5234] Crocker, D. and P. Overell, "Augmented BNF for Syntax Specifications: ABNF", STD 68, RFC 5234, January 2008. [RFC5246] Dierks, T. and E. Rescorla, "The Transport Layer Security (TLS) Protocol Version 1.2", RFC 5246, August 2008. [RFC5322] Resnick, P., Ed., "Internet Message Format", RFC 5322, October 2008. [RFC5646] Phillips, A. and M. Davis, "Tags for Identifying Languages", BCP 47, RFC 5646, September 2009.
[RFC5888] Camarillo, G. and H. Schulzrinne, "The Session Description Protocol (SDP) Grouping Framework", RFC 5888, June 2010. [RFC5905] Mills, D., Martin, J., Burbank, J., and W. Kasch, "Network Time Protocol Version 4: Protocol and Algorithms Specification", RFC 5905, June 2010. [RFC5922] Gurbani, V., Lawrence, S., and A. Jeffrey, "Domain Certificates in the Session Initiation Protocol (SIP)", RFC 5922, June 2010. [RFC6265] Barth, A., "HTTP State Management Mechanism", RFC 6265, April 2011. [W3C.REC-semantic-interpretation-20070405] Tichelen, L. and D. Burke, "Semantic Interpretation for Speech Recognition (SISR) Version 1.0", World Wide Web Consortium Recommendation REC-semantic- interpretation-20070405, April 2007, <http://www.w3.org/TR/2007/ REC-semantic-interpretation-20070405>. [W3C.REC-speech-grammar-20040316] McGlashan, S. and A. Hunt, "Speech Recognition Grammar Specification Version 1.0", World Wide Web Consortium Recommendation REC-speech-grammar-20040316, March 2004, <http://www.w3.org/TR/2004/REC-speech-grammar-20040316>. [W3C.REC-speech-synthesis-20040907] Walker, M., Burnett, D., and A. Hunt, "Speech Synthesis Markup Language (SSML) Version 1.0", World Wide Web Consortium Recommendation REC-speech-synthesis-20040907, September 2004, <http://www.w3.org/TR/2004/REC-speech-synthesis-20040907>. [W3C.REC-xml-names11-20040204] Layman, A., Bray, T., Hollander, D., and R. Tobin, "Namespaces in XML 1.1", World Wide Web Consortium First Edition REC-xml-names11-20040204, February 2004, <http://www.w3.org/TR/2004/REC-xml-names11-20040204>.17.2. Informative References
[ISO.8601.1988] International Organization for Standardization, "Data elements and interchange formats - Information interchange - Representation of dates and times", ISO Standard 8601, June 1988.
[Q.23] International Telecommunications Union, "Technical Features of Push-Button Telephone Sets", ITU-T Q.23, 1993. [RFC2046] Freed, N. and N. Borenstein, "Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types", RFC 2046, November 1996. [RFC2818] Rescorla, E., "HTTP Over TLS", RFC 2818, May 2000. [RFC4217] Ford-Hutchinson, P., "Securing FTP with TLS", RFC 4217, October 2005. [RFC4267] Froumentin, M., "The W3C Speech Interface Framework Media Types: application/voicexml+xml, application/ssml+xml, application/srgs, application/srgs+xml, application/ ccxml+xml, and application/pls+xml", RFC 4267, November 2005. [RFC4301] Kent, S. and K. Seo, "Security Architecture for the Internet Protocol", RFC 4301, December 2005. [RFC4313] Oran, D., "Requirements for Distributed Control of Automatic Speech Recognition (ASR), Speaker Identification/Speaker Verification (SI/SV), and Text-to- Speech (TTS) Resources", RFC 4313, December 2005. [RFC4395] Hansen, T., Hardie, T., and L. Masinter, "Guidelines and Registration Procedures for New URI Schemes", BCP 35, RFC 4395, February 2006. [RFC4463] Shanmugham, S., Monaco, P., and B. Eberman, "A Media Resource Control Protocol (MRCP) Developed by Cisco, Nuance, and Speechworks", RFC 4463, April 2006. [RFC4467] Crispin, M., "Internet Message Access Protocol (IMAP) - URLAUTH Extension", RFC 4467, May 2006. [RFC4733] Schulzrinne, H. and T. Taylor, "RTP Payload for DTMF Digits, Telephony Tones, and Telephony Signals", RFC 4733, December 2006. [RFC4960] Stewart, R., "Stream Control Transmission Protocol", RFC 4960, September 2007. [RFC6454] Barth, A., "The Web Origin Concept", RFC 6454, December 2011.
[W3C.REC-emma-20090210] Johnston, M., Baggia, P., Burnett, D., Carter, J., Dahl, D., McCobb, G., and D. Raggett, "EMMA: Extensible MultiModal Annotation markup language", World Wide Web Consortium Recommendation REC-emma-20090210, February 2009, <http://www.w3.org/TR/2009/REC-emma-20090210>. [W3C.REC-pronunciation-lexicon-20081014] Baggia, P., Bagshaw, P., Burnett, D., Carter, J., and F. Scahill, "Pronunciation Lexicon Specification (PLS)", World Wide Web Consortium Recommendation REC-pronunciation-lexicon-20081014, October 2008, <http://www.w3.org/TR/2008/ REC-pronunciation-lexicon-20081014>. [W3C.REC-voicexml20-20040316] Danielsen, P., Porter, B., Hunt, A., Rehor, K., Lucas, B., Burnett, D., Ferrans, J., Tryphonas, S., McGlashan, S., and J. Carter, "Voice Extensible Markup Language (VoiceXML) Version 2.0", World Wide Web Consortium Recommendation REC-voicexml20-20040316, March 2004, <http://www.w3.org/TR/2004/REC-voicexml20-20040316>. [refs.javaSpeechGrammarFormat] Sun Microsystems, "Java Speech Grammar Format Version 1.0", October 1998.
Appendix A. Contributors
Pierre Forgues Nuance Communications Ltd. 1500 University Street Suite 935 Montreal, Quebec Canada H3A 3S7 EMail: forgues@nuance.com Charles Galles Intervoice, Inc. 17811 Waterview Parkway Dallas, Texas 75252 USA EMail: charles.galles@intervoice.com Klaus Reifenrath Scansoft, Inc Guldensporenpark 32 Building D 9820 Merelbeke Belgium EMail: klaus.reifenrath@scansoft.comAppendix B. Acknowledgements
Andre Gillet (Nuance Communications) Andrew Hunt (ScanSoft) Andrew Wahbe (Genesys) Aaron Kneiss (ScanSoft) Brian Eberman (ScanSoft) Corey Stohs (Cisco Systems, Inc.) Dave Burke (VoxPilot) Jeff Kusnitz (IBM Corp) Ganesh N. Ramaswamy (IBM Corp) Klaus Reifenrath (ScanSoft) Kristian Finlator (ScanSoft) Magnus Westerlund (Ericsson) Martin Dragomirecky (Cisco Systems, Inc.) Paolo Baggia (Loquendo) Peter Monaco (Nuance Communications) Pierre Forgues (Nuance Communications)
Ran Zilca (IBM Corp) Suresh Kaliannan (Cisco Systems, Inc.) Skip Cave (Intervoice, Inc.) Thomas Gal (LumenVox) The chairs of the SPEECHSC work group are Eric Burger (Georgetown University) and Dave Oran (Cisco Systems, Inc.). Many thanks go in particular to Robert Sparks, Alex Agranovsky, and Henry Phan, who were there at the end to dot all the i's and cross all the t's.Authors' Addresses
Daniel C. Burnett Voxeo 189 South Orange Avenue #1000 Orlando, FL 32801 USA EMail: dburnett@voxeo.com Saravanan Shanmugham Cisco Systems, Inc. 170 W. Tasman Dr. San Jose, CA 95134 USA EMail: sarvi@cisco.com