Re: [emma] Loquendo Implementation Report for EMMA 1.0 Specification

Dear Michael,

We accept all the resolution. Many thanks.

We hope that EMMA 1.0 will soon become W3C Recommendation
for the benefit of the whole world of the speech
and multimodal applications. For instance MRCP version 2.

Paolo Baggia
Director of International Standards
Loquendo

--------------------------
From: JOHNSTON, MICHAEL J (MICHAEL J) <johnston@research.att.com>
Date: Thu, 2 Oct 2008 15:54:46 -0400

Many thanks for your support of EMMA. The specific comments
your bring up have been discussed in detail by the
EMMA subgroup and they have formulated the following
responses. Could you please confirm on the public list,
www-multimodal@w3.org if this resolution of the issues is
acceptable.

1.1. TA #606 : Unable to create an epsilon transition emma:arc without
content. Should this be optional?

RESPONSE: The test assertion only applies if the implementation creates
an epsilon transition, so it can remain required for those
implementations.

1.2 TA #1501 : There is no evidence in EMMA 1.0 CR of this statement.
Loquendo asks to remove this Test Assertion from EMMA IR.

RESPONSE: We agree and have removed this test assertion.

1.3 TA #2100 and #2101 : Note that it is
very hard to have absolute times in a client- server ASR implementation.

RESPONSE: We recognize this and note that the spec includes the
following language in Section 4.2.10.2: "Timestamps of inputs collected
by different devices will be subject to variation if the times
maintained by the devices are not synchronized. This concern is outside
of the scope of the EMMA specification."


best
Michael Johnston
on behalf of the EMMA subgroup

Loquendo Speech Technologies

Executive Summary

Loquendo is a strong believer in the considerable advantages that speech
and multimodal standards can bring to speech markets, and continues to
actively support their development and deployment. As a participating
member of the W3C Multimodal Interaction working group, Loquendo
welcomes the Extensible MultiModal Annotation (EMMA) 1.0 Candidate
Recommendation.

EMMA 1.0 allows to create rich annotations for inputs of different
modalities within a Multimodal Application. For instance, EMMA 1.0 is
used as an annotation format for speech and DTMF input within Media
Resource Control Protocol version 2 (MRCPv2). However, EMMA can also be
used by gesture or pen modalities, and it offers interesting features to
represent complex semantic information within an Interaction Manager.

Loquendo is very pleased to be able to contribute by submitting an EMMA
1.0 Implementation Report which covers the relevant features for an EMMA
producer of voice and DTMF results. EMMA 1.0 results are already
available for the Loquendo MRCP Server (a.k.a. Loquendo Speech Suite) to
promote its quick adoption for the benefit of the speech market,
especially for the integration of advanced speech technologies by means
of MRCPv2 protocol in present and future platforms, both in speech /
DTMF contexts and, more in general, in Multimodal application contexts.

Loquendo is continuing to give its complete and wholehearted support to
the work of the W3C Multimodal Interaction and Voice Browser working
groups, as well as to the IETF and the Voice XML Forum, as part of its
continuing commitment and participation in the evolution of this and
other standards.

Technical Details

Loquendo's EMMA results are focused on the production of EMMA markup
in a speech and DTMF context. A few points that should be noted are:

-       TA #301 : N-best interpretations within emma:one-of element
      are ordered best-first in document order on an acoustic
      score criteria, even if emma:confidence is present.
-       TA #606 : Unable to create an epsilon transition emma:arc
      without content. Should this be optional?
-       TA #1501 : There is no evidence in EMMA 1.0 CR of this
statement.
      Loquendo asks to remove this Test Assertion from EMMA IR.
-       TA #2100 and #2101 : Note that it is very hard to have absolute
      times in a client- server ASR implementation.
-       TA #2500 : The lattice included emma:cost annotations, but the
      current value was fixed. In future it will contain the actual
cost.
-       Some annotations are under consideration for future
implementations,
      e.g. emma:model, emma:grammar, emma:info, emma:process,
emma:signal,
      emma:signal-size, emma:media-type, emma:source, emma:start,
emma:end,
      emma:dialog-turn.

Paolo Baggia, Loquendo


Gruppo Telecom Italia - Direzione e coordinamento di Telecom Italia
S.p.A.

Received on Tuesday, 7 October 2008 10:48:02 UTC