Tomohiro Nakatani

Tomohiro Nakatani

Auto-generated profile, based on publicly available information

Tomohiro Nakatani

NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2010 in IEEE Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
TNTomohiro Nakatani
Tomohiro Nakatani
TYTakuya Yoshioka
Takuya Yoshioka
KKKeisuke Kinoshita
Keisuke Kinoshita
MMMasato Miyoshi
Masato Miyoshi
BJBiing-Hwang Juang
Biing-Hwang Juang
This paper proposes a statistical model-based speech dereverberation approach that can cancel the late reverberation of a reverberant speech signal captured by distant microphones without prior knowledge of the room impulse responses. With this approach, the generative model of the captured signal is composed of a source process, which is assumed to be a Gaussian process with a time-varying variance, and an observation process modeled by a delayed linear prediction (DLP). The optimization objective for the dereverberation problem is derived to be the sum of the squared prediction errors normalized by the source variances; hence, this approach is referred to as variance-normalized delayed linear prediction (NDLP). Inheriting the characteristic of DLP, NDLP can robustly estimate an inverse system for late reverberation in the presence of noise without greatly distorting a direct speech signal. In addition, owing to the use of variance normalization, NDLP allows us to improve the dereverberation result especially with relatively short (of the order of a few seconds) observations. Furthermore, NDLP can be implemented in a computationally efficient manner in the time-frequency domain. Experimental results demonstrate the effectiveness and efficiency of the proposed approach in comparison with two existing approaches.

13 June 2019 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
KZKaterina Zmolikova
Katerina Zmolikova
MDMarc Delcroix
Marc Delcroix
KKKeisuke Kinoshita
Keisuke Kinoshita
TOTsubasa Ochiai
Tsubasa Ochiai
TNTomohiro Nakatani
Tomohiro Nakatani
HCHonza Cernocky
Honza Cernocky
The processing of speech corrupted by interfering overlapping speakers is one of the challenging problems as regards today's automatic speech recognition systems. Recently, approaches based on deep learning have made great progress towards solving this problem. Most of these approaches tackle the problem as speech separation, i.e. they blindly recover all the speakers from the mixture. In some scenarios, such as smart personal devices, we may however be interested in recovering one target speaker from a mixture. In this paper, we introduce SpeakerBeam, a method for extracting a target speaker from the mixture based on an adaptation utterance spoken by the target speaker. Formulating the problem as speaker extraction avoids certain issues such as label permutation and the need to determine the number of speakers in the mixture. With SpeakerBeam, we jointly learn to extract a representation from the adaptation utterance characterizing the target speaker and to use this representation to extract the speaker. We explore several ways to do this, mostly inspired by speaker adaptation in acoustic models for automatic speech recognition. We evaluate the performance on the widely used WSJ0-2mix and WSJ0-3mix datasets, and these datasets modified with more noise or more realistic overlapping patterns. We further analyze the learned behavior by exploring the speaker representations and assessing the effect of the length of the adaptation data. The results show the benefit of including speaker information in the processing and the effectiveness of the proposed method.

18 October 2012 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
TYTakuya Yoshioka
Takuya Yoshioka
ASArmin Sehr
Armin Sehr
MDMarc Delcroix
Marc Delcroix
KKKeisuke Kinoshita
Keisuke Kinoshita
RMRoland Maas
Roland Maas
WKWalter Kellermann
Walter Kellermann
Speech recognition technology has left the research laboratory and is increasingly coming into practical use, enabling a wide spectrum of innovative and exciting voice-driven applications that are radically changing our way of accessing digital services and information. Most of today's applications still require a microphone located near the talker. However, almost all of these applications would benefit from distant-talking speech capturing, where talkers are able to speak at some distance from the microphones without the encumbrance of handheld or body-worn equipment [1]. For example, applications such as meeting speech recognition, automatic annotation of consumer-generated videos, speech-to-speech translation in teleconferencing, and hands-free interfaces for controlling consumer-products, like interactive TV, will greatly benefit from distant-talking operation. Furthermore, for a number of unexplored but important applications, distant microphones are a prerequisite. This means that distant talking speech recognition technology is essential for extending the availability of speech recognizers as well as enhancing the convenience of existing speech recognition applications.

1 November 2019 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
RHReinhold Haeb-Umbach
Reinhold Haeb-Umbach
SWShinji Watanabe
Shinji Watanabe
TNTomohiro Nakatani
Tomohiro Nakatani
MBMichiel Bacchiani
Michiel Bacchiani
BHBjorn Hoffmeister
Bjorn Hoffmeister
MSMehrez Souden
Mehrez Souden

1 December 2015
Verified
Conference Paper
Closed access
TYTakuya Yoshioka
Takuya Yoshioka
NINobutaka Ito
Nobutaka Ito
MDMarc Delcroix
Marc Delcroix
AOAtsunori Ogawa
Atsunori Ogawa
KKKeisuke Kinoshita
Keisuke Kinoshita
TNTomohiro Nakatani
Tomohiro Nakatani
CHiME-3 is a research community challenge organised in 2015 to evaluate speech recognition systems for mobile multi-microphone devices used in noisy daily environments. This paper describes NTT's CHiME-3 system, which integrates advanced speech enhancement and recognition techniques. Newly developed techniques include the use of spectral masks for acoustic beam-steering vector estimation and acoustic modelling with deep convolutional neural networks based on the "network in network" concept. In addition to these improvements, our system has several key differences from the official baseline system. The differences include multi-microphone training, dereverberation, and cross adaptation of neural networks with different architectures. The impacts that these techniques have on recognition performance are investigated. By combining these advanced techniques, our system achieves a 3.45% development error rate and a 5.83% evaluation error rate. Three simpler systems are also developed to perform evaluations with constrained set-ups.

1 March 2016
Verified
Conference Paper
Closed access
THTakuya Higuchi
Takuya Higuchi
NINobutaka Ito
Nobutaka Ito
TYTakuya Yoshioka
Takuya Yoshioka
TNTomohiro Nakatani
Tomohiro Nakatani
This paper considers acoustic beamforming for noise robust automatic speech recognition (ASR). A beamformer attenuates background noise by enhancing sound components coming from a direction specified by a steering vector. Hence, accurate steering vector estimation is paramount for successful noise reduction. Recently, a beamforming approach was proposed that employs time-frequency masks. In the speech recognition system we submitted to the CHiME-3 Challenge, we employed a new form of this approach that uses a speech spectral model based on a complex Gaussian mixture model (CGMM) to estimate the time-frequency masks and the steering vector without providing technical details. This paper elaborates on this technique and examines its effectiveness for ASR. Experimental results show that the CGMM-based approach outperforms a recently proposed mask estimator based on a Watson mixture model. In addition, the CGMM-based approach is extended to an online speech enhancement scenario, which allows this technique to be used in an online recognition setup. This online version reduces the CHiME-3 evaluation error rate from 15.60% to 8.47%, which is a comparable improvement to that obtained by batch processing.