Probabilistic Integration of Partial Lexical Information for Noise Robust Haptic Voice Recognition
Sim, Khe Chai

Article Structure

Abstract

This paper presents a probabilistic framework that combines multiple knowledge sources for Haptic Voice Recognition (HVR), a multimodal input method designed to provide efficient text entry on modern mobile devices.

Introduction

Nowadays, modern portable devices, such as the smartphones and tablets, are equipped with microphone and touchscreen display.

Noise Robust ASR

As previously mentioned, the process of converting speech into text using ASR is error-prone, where significant performance degradation is often due to the presence of noise or other acoustic interference.

Haptic Voice Recognition (HVR)

For many voice-enabled applications, users often find voice input to be a black box that captures the users’ voice and automatically converts it into texts using ASR.

A Probabilistic Formulation for HVR

Let 0 = {01,02, .

Integration of Knowledge Sources

As previously mentioned, the HVR recognition process involves maximising the posterior probability in Eq.

Experimental Results

In this section, experimental results are reported based on the data collected using a prototype HVR interface implemented on an iPad.

Conclusions

This paper has presented a unifying probabilistic framework for the multimodal Haptic Voice Recognition (HVR) interface.

Topics

language model

Appears in 12 sentences as: Language model (1) language model (8) language models (3)
In Probabilistic Integration of Partial Lexical Information for Noise Robust Haptic Voice Recognition
  1. In addition to the acoustic and language models used in automatic speech recognition systems, HVR uses the haptic and partial lexical models as additional knowledge sources to reduce the recognition search space and suppress confusions.
    Page 1, “Abstract”
  2. In addition to the acoustic model and language model used in ASR, haptic model and partial lexical model are also introduced to facilitate the integration of more sophisticated haptic events, such as the keystrokes, into HVR.
    Page 2, “Introduction”
  3. In conventional ASR, acoustically similar word sequences are typically resolved implicitly using a language model where contexts of neighboring words are used for disambiguation.
    Page 3, “Haptic Voice Recognition (HVR)”
  4. where P(W) can be modelled by the word-based 77.-gram language model (Chen and Goodman, 1996) commonly used in automatic speech recognition.
    Page 3, “A Probabilistic Formulation for HVR”
  5. 0 Language model score: P(W)
    Page 4, “A Probabilistic Formulation for HVR”
  6. Note that the acoustic model and language model scores are already used in the conventional ASR.
    Page 4, “A Probabilistic Formulation for HVR”
  7. where fl, 5, 75 and 7:1 denote the WFST representation of the acoustic model, language model , PLI model and haptic model respectively.
    Page 5, “Integration of Knowledge Sources”
  8. (2002) has shown that Hidden Markov Models (HMMs) and n-gram language models can be viewed as WFSTs.
    Page 5, “Integration of Knowledge Sources”
  9. These sentences contain a variety of given names, surnames and city names so that confusions cannot be easily resolved using a language model .
    Page 6, “Experimental Results”
  10. The ASR system used in all the experiments reported in this paper consists of a set of HMM-based triphone acoustic models and an n-gram language model .
    Page 6, “Experimental Results”
  11. A bigram language model with a vocabulary size of 200 words was used for testing.
    Page 6, “Experimental Results”

See all papers in Proc. ACL 2012 that mention language model.

See all papers in Proc. ACL that mention language model.

Back to top.

model score

Appears in 6 sentences as: model score (7) model scores (1)
In Probabilistic Integration of Partial Lexical Information for Noise Robust Haptic Voice Recognition
  1. 0 Acoustic model score: p(O|W) o Haptic model score : p(H|£)
    Page 4, “A Probabilistic Formulation for HVR”
  2. o PLI model score : P(£|W)
    Page 4, “A Probabilistic Formulation for HVR”
  3. 0 Language model score : P(W)
    Page 4, “A Probabilistic Formulation for HVR”
  4. Note that the acoustic model and language model scores are already used in the conventional ASR.
    Page 4, “A Probabilistic Formulation for HVR”
  5. The probabilistic formulation of HVR incorporated two additional probabilities: haptic model score, p(H|£) and PL] model score , P(£|W).
    Page 4, “A Probabilistic Formulation for HVR”
  6. Since each word is represented by a unique PLI (the initial letter) in this work, the PLI model score is given by
    Page 4, “A Probabilistic Formulation for HVR”

See all papers in Proc. ACL 2012 that mention model score.

See all papers in Proc. ACL that mention model score.

Back to top.

probabilistic models

Appears in 3 sentences as: probabilistic model (1) probabilistic models (2)
In Probabilistic Integration of Partial Lexical Information for Noise Robust Haptic Voice Recognition
  1. This framework allows coherent probabilistic models of different knowledge sources to be tightly integrated.
    Page 2, “Introduction”
  2. Therefore, fl, 5, and 7:1 can be obtained from the respective probabilistic models .
    Page 5, “Integration of Knowledge Sources”
  3. Therefore, apart from the acoustic and language models used in conventional ASR, HVR also combines the haptic model as well as the PLI model to yield an integrated probabilistic model .
    Page 8, “Conclusions”

See all papers in Proc. ACL 2012 that mention probabilistic models.

See all papers in Proc. ACL that mention probabilistic models.

Back to top.

PDF available from www.aclweb.org.
Send us an email