wdiff draft-ietf-avt-dsr-04.txt draft-ietf-avt-dsr-05.txt

Internet Engineering Task Force Q. Xie (Editor)
Audio Video Transport WG Motorola, Inc.
INTERNET-DRAFT

ExpiresA new Request for Comments is now available in six months October 4, 2002 online RFC libraries.

RFC 3557

Title: RTP Payload Format for ETSI European Telecommunications
Standards Institute (ETSI) European Standard
ES 201 108 Distributed Speech Recognition Encoding
<draft-ietf-avt-dsr-04.txt>

Status of this Memo

This document is an Internet-Draft and is in full conformance with
all provisions of Section 10 of [RFC2026].

Internet-Drafts are working documents of the Internet Engineering
Task Force (IETF), its areas, and its working groups. Note that
other groups may also distribute working documents as Internet-
Drafts. Internet-Drafts are draft documents valid for a maximum of
six months and may be updated, replaced, or obsoleted by other
documents at any time. It is inappropriate to use Internet- Drafts
as reference material or to cite them other than as "work in
progress."

The list of current Internet-Drafts can be accessed at
http://www.ietf.org/ietf/1id-abstracts.txt
The list of Internet-Draft Shadow Directories can be accessed at
http://www.ietf.org/shadow.html.

Abstract
Author(s): Q. Xie, Ed.
Status: Standards Track
Date: July 2003
Mailbox: Qiaobing.Xie@motorola.com
Pages: 15
Characters: 29692
Updates/Obsoletes/SeeAlso: None

I-D Tag: draft-ietf-avt-dsr-05.txt

URL: ftp://ftp.rfc-editor.org/in-notes/rfc3557.txt

This document specifies an RTP payload format for encapsulating ETSI
European Telecommunications Standards Institute (ETSI) European
Standard ES (ES) 201 108 front-end signal processing feature streams
for distributed speech recognition (DSR) systems.

1. Conventions and Acronyms

The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
"SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in
this

This document are to be interpreted as described in [RFC2119].

The following acronyms are used in this document:
DSR - Distributed Speech Recognition
ETSI - the European Telecommunications Standards Institute
FP - Frame Pair
DTX - Discontinuous Transmission

2. Introduction

Motivated by technology advances in the field of speech recognition,
voice interfaces to services (such as airline information systems,
unified messaging) are becoming more prevalent. In parallel, the
popularity of mobile devices has also increased dramatically. However,
the voice codecs typically employed in mobile devices were designed to
optimize audible voice quality and not speech recognition accuracy,
and using these codecs with speech recognizers can result in poor
recognition performance. For systems that can be accessed from
heterogeneous networks using multiple speech codecs, recognition
system designers are further challenged to accommodate the
characteristics of these differences in a robust manner. Channel
errors and lost data packets in these networks result in further
degradation of the speech signal.

In traditional systems as described above, the entire speech
recognizer lies on the server. It is forced to use incoming speech in
whatever condition it arrives after the network decodes the vocoded
speech. To address this problem, we use a distributed speech
recognition (DSR) architecture. In such a system, the remote device acts as
a thin client, also known as the front-end, in communication with a
speech recognition server, also called a speech engine. The remote
device processes the speech, compresses the data, and adds error
protection to the bitstream in a manner optimal for speech
recognition. The speech engine then uses this representation directly,
minimizing the signal processing necessary and benefiting from
enhanced error concealment.

To achieve interoperability with different client devices and speech
engines, a common format is needed. Within product of the "Aurora" DSR working
group Audio/Video Transport Working Group
of the European Telecommunications Standards Institute (ETSI), a
payload has been defined and was published as a standard [ES201108] in
February 2000.

For voice dialogues between a caller and a voice service, low latency IETF.

This is now a high priority along with accurate speech recognition. While
jitter in the speech recognizer input is not particularly important,
many issues related to speech interaction over an IP-based connection
are still relevant. Therefore, it is desirable to use the DSR payload
in an RTP-based session.

2.1. ETSI ES 201 108 DSR Front-end Codec

The ETSI Proposed Standard ES 201 108 Protocol.

This document specifies an Internet standards track protocol for DSR [ES201108] defines a signal
processing front-end
the Internet community, and compression scheme for speech input to a
speech recognition system. Some relevant characteristics of this ETSI
DSR front-end codec are summarized below.

The coding algorithm, a standard mel-cepstral technique common to many
speech recognition systems, supports three raw sampling rates: 8 kHz,
11 kHz, requests discussion and 16 kHz. The mel-cepstral calculation is a frame-based
scheme that produces an output vector every 10 ms.

After calculation of the mel-cepstral representation, the
representation is first quantized via split-vector quantization suggestions
for improvements. Please refer to
reduce the data rate of the encoded stream. Then, the quantized
vectors from two consecutive frames are put into an FP, as
described in more detail in Section 4.1.

2.2 Typical Scenarios for Using DSR Payload Format

The diagrams in Figure 1 show some typical use scenarios current edition of the ES 201
108 DSR RTP payload format.

a) IP user terminal to IP speech engine

b) non-IP user terminal to IP speech engine via a gateway

c) IP user terminal to non-IP speech engine via a gateway

Figure 1: Typical Scenarios
"Internet Official Protocol Standards" (STD 1) for Using DSR Payload Format.

For the different scenarios in Figure 1, the speech recognizer always
resides in the speech engine. A DSR front-end encoder inside the User
Terminal performs front-end speech processing
standardization state and sends the resultant
data to the speech engine in the form of "frame pairs" (FPs). Each FP
contains two sets status of encoded speech vectors representing 20ms of
original speech.

3. ES 201 108 DSR RTP Payload Format

An ES 201 108 DSR RTP payload datagram consists of a standard RTP
header [RFC1889] followed by a DSR payload. The DSR payload itself is
formed by concatenating a series of ES 201 108 DSR FPs (defined in
Section 4).

FPs are always packed bit-contiguously into the payload octets
beginning with the most significant bit. For ES 201 108 front-end, the
size this protocol. Distribution
of each FP this memo is 96 bits or 12 octets (see Sections 4.1 and
4.2). unlimited.

This ensures that a DSR payload will always end on an octet
boundary.

The following example shows a DSR RTP datagram carrying a DSR payload
containing three 96-bit-long FPs (bit 0 announcement is the MSB):

0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
\ \
/ RTP header in [RFC1889] /
\ \
+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
| |
+ +
| FP #1 (96 bits) |
+ +
| |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| |
+ +
| FP #2 (96 bits) |
+ +
| |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| |
+ +
| FP #3 (96 bits) |
+ +
| |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

Figure 2. An example of an ES 201 108 DSR RTP payload.

3.1. Consideration on Number of FPs in Each RTP Packet

The number of FPs per payload packet should be determined by the
latency and bandwidth requirements of the DSR application using this
payload format. In particular, using a smaller number of FPs per
payload packet in a session will result in lowered bandwidth
efficiency due sent to the RTP/UDP/IP header overhead, while using a larger
number of FPs per packet will cause longer end-to-end delay IETF list and hence
increased recognition latency. Furthermore, carrying a larger number of
FPs per packet will increase the possibility of catastrophic packet
loss; the loss of a large number of consecutive FPs is a situation
most speech recognizers have difficulty dealing with.

It is therefore RECOMMENDED that the number of FPs per DSR payload
packet be minimized, subject to meeting the application's requirements
on network bandwidth efficiency. RTP header compression techniques,
such as those defined in [RFC2508] and [RFC3095], should be considered RFC-DIST list.
Requests to improve network bandwidth efficiency.

3.2. Support for Discontinuous Transmission

The DSR RTP payloads may be used to support discontinuous transmission
(DTX) of speech, which allows that DSR FPs are sent only when speech
has been detected at the terminal equipment.

In DTX a set of DSR frames coding an unbroken speech segment
transmitted from the terminal added to the server is called a transmission
segment. A DSR frame inside such a transmission segment can be
either a speech frame or a non-speech frame, depending on the nature
of the section of the speech signal it represents.

The end of a transmission segment is determined at the sending end
equipment when the number of consecutive non-speech frames exceeds a
pre-set threshold, called the hangover time. A typical value used for
the hangover time is 1.5 seconds.

After all FPs in a transmission segment are sent, the front-end SHOULD
indicate the end of the current transmission segment by sending one or
more Null FPs (defined in Section 4.2).

4. Frame Pair Formats

4.1. Format of Speech and Non-speech FPs

The following mel-cepstral frame MUST be used, as defined in
[ES201108]:

0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| idx(0,1) | idx(2,3) | idx(4,5) | idx(6,7) | idx(8,9) |idx
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
(10,11) | idx(12,13) |
+-+-+-+-+-+-+-+-+-+-+-+-+

The length of a frame is 44 bits representing 10ms of voice.

As defined in [ES201108], pairs of deleted from the quantized 10ms mel-cepstral
frames MUST be grouped together and protected with a 4-bit CRC,
forming a 92-bit long FP:

0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| Frame #1 (44 bits) |
+ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| | Frame #2 (44 bits) |
+-+-+-+-+-+-+-+-+-+-+-+-+ +-+-+-+-+-+-+-+-+
| | CRC |0|0|0|0|
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+

Therefore, each FP represents 20ms of original speech. Note, as shown
above, each FP MUST IETF distribution list
should be padded with 4 zeros sent to the end in order IETF-REQUEST@IETF.ORG. Requests to make
it aligned be
added to the 32-bit word boundary. This makes the size of an FP
96 bits, or 12 octets. Note, this padding is separate deleted from padding
indicated by the P bit in the RTP header.

The 4-bit CRC MUST RFC-DIST distribution list should
be calculated using the formula defined in 6.2.4 in
[ES201108].

4.2. Format of Null FP

A Null FP for the ES 201 108 front-end codec is defined by setting the
content of the first and second frame in the FP sent to null (i.e., filling
the first 88 bits of the FP with 0's). The 4-bit CRC MUST be
calculated the same way as described in 6.2.4 in [ES201108], and 4
zeros MUST RFC-DIST-REQUEST@RFC-EDITOR.ORG.

Details on obtaining RFCs via FTP or EMAIL may be padded to the end of the Null FP to made it 32-bit word
aligned.

4.3. RTP header usage

The format of the RTP header is specified in [RFC1889]. This payload
format uses the fields of the header in a manner consistent with that
specification.

The RTP timestamp corresponds to the sampling instant of the first
sample encoded for the first FP in the packet. The timestamp
clock frequency is the same as the sampling frequency, so the
timestamp unit is in samples.

As defined obtained by ES 201 108 front-end codec, the duration of one FP is 20
ms, corresponding sending
an EMAIL message to 160, 220, or 320 encoded samples rfc-info@RFC-EDITOR.ORG with sampling
rate of 8, 11, or 16 kHz being used at the front-end, respectively.
Thus, the timestamp is increased by 160, 220, or 320 for each
consecutive FP, respectively.

The DSR payload for ES 201 108 front-end codes is always an integral
number of octets. If additional padding is required message body
help: ways_to_get_rfcs. For example:

To: rfc-info@RFC-EDITOR.ORG
Subject: getting rfcs

help: ways_to_get_rfcs

Requests for some other
purpose, then the P bit in the RTP in the header may be set and
padding appended as specified in [RFC1889].

The RTP header marker bit (M) special distribution should be set following the general
rules defined in [RFC1890new].

The assignment of an RTP payload type for this new packet format is
outside the scope of this document, and will not be specified here. It
is expected that the RTP profile under which this payload format is
being used will assign a payload type for this encoding or specify
that the payload type is addressed to be bound dynamically.

5. DSR MIME Type Registration

Media Type name: audio

Media subtype name: dsr-es201108

Required parameters: none

Optional parameters for RTP mode:

rate: Indicates the sample rate of the speech. Valid values include:
8000, 11000, and 16000. If this parameter is not present,
8000 sample rate is assumed.

maxptime: The maximum amount of media which can be encapsulated in
each packet, expressed as time in milliseconds. The time shall
be calculated as the sum of the time the media present in the
packet represents. The time SHOULD be a multiple of the frame
pair size (i.e., one FP <-> 20ms).

If this parameter is not present, maxptime is assumed to be
80ms.

Note, since the performance of most speech recognizers are
extremely sensitive to consecutive FP losses, if either the user
author of the payload format expects a high packet loss ratio for the
session, it MAY consider to explicitly choose a maxptime
value for the session that is shorter than the default value.

ptime: see RFC2327 [RFC2327].

Encoding considerations : This type is defined for transfer via RTP
[RFC1889] as described in Sections 3 and 4 of RFC XXXX.

Security considerations : See Section 6 of RFC XXXX.

Person & email address to contact for further information:
Qiaobing.Xie@motorola.com

Intended usage: COMMON. It is expected that many VoIP applications
(as well as mobile applications) will use this type.

Author/Change controller:
Qiaobing.Xie@motorola.com
IETF Audio/Video transport working group

5.1. Mapping MIME Parameters into SDP

The information carried in the MIME media type specification has a
specific mapping to fields in the Session Description Protocol (SDP)
[RFC2327], which is commonly used to describe RTP sessions. When SDP is
used question, or to specify sessions employing ES 201 018 DSR codec, the
mapping is as follows:

o The MIME type ("audio") goes in SDP "m=" as the media name.

o The MIME subtype ("dsr-es201108") goes in SDP "a=rtpmap" as the
encoding name.

o The optional parameter "rate" also goes in "a=rtpmap" as clock
rate.

o The optional parameters "ptime" and "maxptime" go in the SDP
"a=ptime" and "a=maxptime" attributes, respectively.

Example of usage of ES 201 108 DSR:

m=audio 49120 RTP/AVP 101
a=rtpmap:101 dsr-es201108/8000
a=maxptime:40

6. Security Considerations

Implementations using RFC-Manager@RFC-EDITOR.ORG. Unless
specifically noted otherwise on the payload defined in this specification RFC itself, all RFCs are
subject to the security considerations discussed in the RTP
specification [RFC1889] and the RTP profile [RFC1890new]. This payload
does not specify any different security services.

7. Contributors

The following individuals contributed to the design of this payload
format and the writing of this document: Q. Xie (Motorola), D. Pearce
(Motorola), S. Balasuriya (Motorola), Y. Kim (VerbalTek), S. H. Maes
(IBM), and, Hari Garudadri (Qualcomm).

8. Acknowledgments

The design presented here benefits greatly from an earlier work on DSR
RTP payload design by Jeff Meunier and Priscilla Walther. The authors
also wish to thank Brian Eberman, John Lazzaro, Magnus Westerlund,
Rainu Pierce, Priscilla Walther, and others for their review and
valuable comments on this document.

9. References

[ES201108] European Telecommunications Standards Institute (ETSI)
Standard ES 201 108, "Speech Processing, Transmission and Quality
Aspects (STQ); Distributed Speech Recognition; Front-end Feature
Extraction Algorithm; Compression Algorithms," Ver. 1.1.2, April
11, 2000. http://webapp.etsi.org/pda/home.asp?wki_id=9948

[RFC1889] H. Schulzrinne, S. Casner, R. Frederick, and V. Jacobson,
"RTP: A transport protocol
unlimited distribution.echo
Submissions for real-time applications," Internet
Draft, Internet Engineering Task Force, Feb. 1999 Work in progress,
revision to RFC 1889.

[RFC2026] Bradner, S., "The Internet Standards Process -- Revision 3",
BCP 9, RFC 2026, October 1996.

[RFC2119] Bradner, S., "Key words Requests for use in RFCs Comments should be sent to Indicate
Requirement Levels", BCP 14,
RFC-EDITOR@RFC-EDITOR.ORG. Please consult RFC 2119, March 1997

[RFC2327] M. Handley and V. Jacobson, "SDP: Session Description
Protocol", IETF RFC 2327, April 1998

9.1. Informative References

[RFC1890new] H. Schulzrinne and S. Casner, "RTP Profile for Audio and
Video Conferences with Minimal Control," Internet Draft
draft-ietf-avt-profile-new-12.txt, Work in Progress November 21,
2000, revision 2223, Instructions to RFC 1890.

[RFC2508] S. Casner and V. Jacobson, "Compressing IP/UDP/RTP Headers
Authors, for Low-Speed Serial Links," RFC 2508, February 1999.

[RFC3095] C. Bormann, C. Burmeister, M. Degermark, H. Fukushima,
H. Hannu, L-E. Jonsson, R. Hakenberg, T. Koren, K. Le, Z. Liu,
A. Martensson, A. Miyazaki, K. Svanbro, T. Wiebke, T. Yoshimura,
and H. Zheng, "RObust Header Compression (ROHC): Framework and four
profiles: RTP, UDP, ESP, and uncompressed," IETF RFC 3095, July
2001.

10. Author's Addresses

Qiaobing Xie Tel: +1-847-632-3028
Motorola, Inc. EMail: Qiaobing.Xie@motorola.com
1501 W. Shure Drive, 2-F9
Arlington Heights, IL 60004, USA

David Pearce Tel: +44 (0)1256 484 436
Motorola Labs EMail: bdp003@motorola.com
UK Research Laboratory
Jays Close
Viables Industrial Estate
Basingstoke, HANTS, RG22 4PD

Senaka Balasuriya Tel: +1-630-353-8347
Motorola, Inc. EMail: Senaka.Balasuriya@motorola.com
1411 Opus Place, Suite 350
Downers Grover, IL 60515, USA

Yoon Kim Tel: +1-408-768-4974
VerbalTek, Inc. EMail: yoonie@verbaltek.com
2921 Copper Rd.
Santa Clara, CA 95051

Stephane H. Maes Tel: +1-914-945-2908
IBM EMail: smaes@us.ibm.com
TJ Watson Research Center
P.O. Box 218,
Yorktown Heights, NY 10598, USA.

Hari Garudadri Tel: +1-858-651-6383
Qualcomm Inc. EMail: hgarudad@qualcomm.com
5775, Morehouse Dr.
San Diego, CA 92121-1714, USA

This Internet Draft expires in 6 months from October 4, 2002 further information.