The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nous présentons une nouvelle méthode discriminante d'adaptation de modèles acoustiques qui traite d'une variabilité de la parole dépendante de la tâche. Nous nous sommes concentrés sur les différences d'expressions ou de styles de parole entre les tâches et avons fixé l'objectif de cette méthode comme améliorant la précision de la reconnaissance de phrases indistinctement prononcées en fonction d'un style de parole. L'adaptation ajoute des modèles de sous-mots pour les variantes de sous-mots fréquemment observables dans la tâche. Pour trouver les variantes dépendant de la tâche, les mots à faible confiance sont sélectionnés statistiquement parmi les mots ayant une fréquence plus élevée dans les données d'adaptation de la tâche en utilisant leurs réseaux de mots. Les paramètres HMM de modèles de sous-mots dépendant des mots sont entraînés de manière discriminante à l'aide de transformations linéaires avec un critère d'erreur phonétique minimale (MPE). Pour la formation MPE, la précision des sous-mots discriminant les variantes et les originaux est également étudiée. Dans les expériences de reconnaissance vocale, l'adaptation proposée avec les variantes de sous-mots a réduit le taux d'erreur de mot de 12.0 % par rapport dans une tâche de diffusion conversationnelle japonaise.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Shoei SATO, Takahiro OKU, Shinichi HOMMA, Akio KOBAYASHI, Toru IMAI, "Learning Speech Variability in Discriminative Acoustic Model Adaptation" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 9, pp. 2370-2378, September 2010, doi: 10.1587/transinf.E93.D.2370.
Abstract: We present a new discriminative method of acoustic model adaptation that deals with a task-dependent speech variability. We have focused on differences of expressions or speaking styles between tasks and set the objective of this method as improving the recognition accuracy of indistinctly pronounced phrases dependent on a speaking style. The adaptation appends subword models for frequently observable variants of subwords in the task. To find the task-dependent variants, low-confidence words are statistically selected from words with higher frequency in the task's adaptation data by using their word lattices. HMM parameters of subword models dependent on the words are discriminatively trained by using linear transforms with a minimum phoneme error (MPE) criterion. For the MPE training, subword accuracy discriminating between the variants and the originals is also investigated. In speech recognition experiments, the proposed adaptation with the subword variants reduced the word error rate by 12.0% relative in a Japanese conversational broadcast task.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.2370/_p
Copier
@ARTICLE{e93-d_9_2370,
author={Shoei SATO, Takahiro OKU, Shinichi HOMMA, Akio KOBAYASHI, Toru IMAI, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Speech Variability in Discriminative Acoustic Model Adaptation},
year={2010},
volume={E93-D},
number={9},
pages={2370-2378},
abstract={We present a new discriminative method of acoustic model adaptation that deals with a task-dependent speech variability. We have focused on differences of expressions or speaking styles between tasks and set the objective of this method as improving the recognition accuracy of indistinctly pronounced phrases dependent on a speaking style. The adaptation appends subword models for frequently observable variants of subwords in the task. To find the task-dependent variants, low-confidence words are statistically selected from words with higher frequency in the task's adaptation data by using their word lattices. HMM parameters of subword models dependent on the words are discriminatively trained by using linear transforms with a minimum phoneme error (MPE) criterion. For the MPE training, subword accuracy discriminating between the variants and the originals is also investigated. In speech recognition experiments, the proposed adaptation with the subword variants reduced the word error rate by 12.0% relative in a Japanese conversational broadcast task.},
keywords={},
doi={10.1587/transinf.E93.D.2370},
ISSN={1745-1361},
month={September},}
Copier
TY - JOUR
TI - Learning Speech Variability in Discriminative Acoustic Model Adaptation
T2 - IEICE TRANSACTIONS on Information
SP - 2370
EP - 2378
AU - Shoei SATO
AU - Takahiro OKU
AU - Shinichi HOMMA
AU - Akio KOBAYASHI
AU - Toru IMAI
PY - 2010
DO - 10.1587/transinf.E93.D.2370
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2010
AB - We present a new discriminative method of acoustic model adaptation that deals with a task-dependent speech variability. We have focused on differences of expressions or speaking styles between tasks and set the objective of this method as improving the recognition accuracy of indistinctly pronounced phrases dependent on a speaking style. The adaptation appends subword models for frequently observable variants of subwords in the task. To find the task-dependent variants, low-confidence words are statistically selected from words with higher frequency in the task's adaptation data by using their word lattices. HMM parameters of subword models dependent on the words are discriminatively trained by using linear transforms with a minimum phoneme error (MPE) criterion. For the MPE training, subword accuracy discriminating between the variants and the originals is also investigated. In speech recognition experiments, the proposed adaptation with the subword variants reduced the word error rate by 12.0% relative in a Japanese conversational broadcast task.
ER -