✦ LIBER ✦

Speaker recognition using HMM composition in noisy environments

✍ Scribed by Tomoko Matsui; Tomohito Kanno; Sadaoki Furui

Publisher: Elsevier Science
Year: 1996
Tongue: English
Weight: 119 KB
Volume: 10
Category: Article
ISSN: 0885-2308
DOI: 10.1006/csla.1996.0007

No coin nor oath required. For personal study only.

✦ Synopsis

This paper investigates a speaker recognition method that is robust against background noise. In noisy environments, one important issue is how to create a model for each speaker so as to compensate for noise. The method described here is based on hidden Markov model (HMM) composition, which combines a speaker HMM and a noisesource HMM into a noise-added speaker HMM with a particular signal-to-noise ratio (SNR). Since it is difficult to measure the SNR of input speech with non-stationary noise exactly, this method creates several noise-added speaker HMMs with various SNRs. The HMM that has the highest likelihood value for the input speech is selected, and a speaker decision is made using this likelihood value.

Experimental application of this method to text-independent speaker identification and verification in various kinds of noisy environments demonstrated considerable improvement in speaker recognition for speech utterances of male speakers.

📜 SIMILAR VOLUMES

Model adaptation by HMM decomposition an

Model adaptation by HMM decomposition and composition in noisy reverberant environments

✍ Tetsuya Takiguchi; Satoshi Nakamura; Kiyohiro Shikano 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 254 KB 👁 1 views

In hands-free speech recognition in which the user speaks at a distance from the microphone, the accuracy of recognition is degraded if the environment is reverberant. The reason for the degradation is that the uttered speech is affected by the surrounding noise and reverberation, which produces a m

Speech recognition based on HMM decompos

Speech recognition based on HMM decomposition and composition method with a microphone array in noisy reverberant environments

✍ Kazuhiko Miki; Takanobu Nishiura; Satoshi Nakamura; Kiyohiro Shikano 📂 Article 📅 2002 🏛 John Wiley and Sons 🌐 English ⚖ 1012 KB

Speech recognition in the noisy car envi

Speech recognition in the noisy car environment

✍ H.W. Ruehl; S. Dobler; J. Weith; P. Meyer; A. Noll; H.H. Hamer; H. Piotrowski 📂 Article 📅 1991 🏛 Elsevier Science 🌐 English ⚖ 622 KB

Speech recognition in noisy environments

Speech recognition in noisy environments with the aid of microphone arrays

✍ Dirk Van Compernolle; Weiye Ma; Fei Xie; Marc Van Diest 📂 Article 📅 1990 🏛 Elsevier Science 🌐 English ⚖ 722 KB

Unsupervised acoustic model adaptation a

Unsupervised acoustic model adaptation algorithm using MLLR in a noisy environment

✍ Miichi Yamada; Akira Baba; Shinichi Yoshizawa; Yuuichiro Mera; Akinobu Lee; Hiro 📂 Article 📅 2006 🏛 John Wiley and Sons 🌐 English ⚖ 981 KB

This paper proposes an unsupervised noisy environment adaptation algorithm based on the HMM acoustic model, using MLLR and a multispeaker database. An arbitrary single sentence uttered by the target speaker, together with living room noise, is used as the input, and the data with superposed noise fo

Improvement of noisy speech recognition

Improvement of noisy speech recognition using a proportional alignment decoding algorithm in the training phase

✍ Wei-Wen Hung; Hsiao-Chuan Wang 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 670 KB

Modelling the state duration of hidden Markov models (HMMs) can effectively improve the accuracy in decoding the state sequence of an utterance and result in an improvement of speech recognition accuracy. However, when a speech signal is contaminated by ambient noise, the decoded state sequence may