Yoichi Yamashita
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yoichi Yamashita has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Takahiro Fukumori
Grad. School of Information Sci. and Eng., Ritsumeikan Univ., 1-1-1 Nojihigashi, Kusatsu 525-8577
5 shared publications - Keisuke Imoto
National Institute of Advanced Industrial Science and Technology (AIST)
3 shared publications Noriyuki Tonami
Ritsumeikan University Japan
2 shared publications- Takanobu Nishiura
College of Information Science and Engineering, Ritsumeikan University, Osaka 567-8570, Japan
2 shared publications Yuki Okamoto
Ritsumeikan University Japan
2 shared publications- Akira Inoue
Tohoku University 2 Institute of Materials Research Sendai, Japan
1 shared publication
Latest Publications
- Open Access
- 2 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 4434-4444
RISC: A Corpus for Shout Type Classification and Shout Intensity Prediction
The detection of shouted speech is crucial in audio surveillance and monitoring. Although it is desirable for a security system to be able to identify emergencies, existing corpora provide only a binary label (i.e., shouted or normal) for each speech sample, making it difficult to predict the shout intensity. Furthermore, most corpora comprise only utterances typical of hazardous situations, meaning that classifiers cannot learn to discriminate such utterances from shouts typical of less hazardous situations such as cheers. Thus, this paper presents a novel research source, the RItsumeikan Shout Corpus (RISC), which contains wide variety types of shouted speech samples collected in recording experiments. Each shouted speech sample in RISC has a shout type and is also assigned shout intensity ratings via a crowdsourcing service. We also present a comprehensive performance comparison among deep learning approaches for speech type classification tasks and a shout intensity prediction task. The results show that feature learning based on the spectral and cepstral domains achieves high performance, no matter which network architecture is used. The results also demonstrate that shout type classification and intensity prediction are still challenging tasks, and RISC is expected to contribute to further development in this research area.
- 2 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 4434-4444
Open AccessRISC: A Corpus for Shout Type Classification and Shout Intensity Prediction
The detection of shouted speech is crucial in audio surveillance and monitoring. Although it is desirable for a security system to be able to identify emergencies, existing corpora provide only a binary label (i.e., shouted or normal) for each speech sample, making it difficult to predict the shout intensity. Furthermore, most corpora comprise only utterances typical of hazardous situations, meaning that classifiers cannot learn to discriminate such utterances from shouts typical of less hazardous situations such as cheers. Thus, this paper presents a novel research source, the RItsumeikan Shout Corpus (RISC), which contains wide variety types of shouted speech samples collected in recording experiments. Each shouted speech sample in RISC has a shout type and is also assigned shout intensity ratings via a crowdsourcing service. We also present a comprehensive performance comparison among deep learning approaches for speech type classification tasks and a shout intensity prediction task. The results show that feature learning based on the spectral and cepstral domains achieves high performance, no matter which network architecture is used. The results also demonstrate that shout type classification and intensity prediction are still challenging tasks, and RISC is expected to contribute to further development in this research area.
- Open Access
Sound Event Detection Guided by Semantic Contexts of Scenes
Some studies have revealed that contexts of scenes (e.g., "home," "office," and "cooking") are advantageous for sound event detection (SED). Mobile devices and sensing technologies give useful information on scenes for SED without the use of acoustic signals. However, conventional methods can employ pre-defined contexts in inference stages but not undefined contexts. This is because one-hot representations of pre-defined scenes are exploited as prior contexts for such conventional methods. To alleviate this problem, we propose scene-informed SED where pre-defined scene-agnostic contexts are available for more accurate SED. In the proposed method, pre-trained large-scale language models are utilized, which enables SED models to employ unseen semantic contexts of scenes in inference stages. Moreover, we investigated the extent to which the semantic representation of scene contexts is useful for SED. Experimental results performed with TUT Sound Events 2016/2017 and TUT Acoustic Scenes 2016/2017 datasets show that the proposed method improves micro and macro F-scores by 4.34 and 3.13 percentage points compared with conventional Conformer- and CNN--BiGRU-based SED, respectively.
Open AccessSound Event Detection Guided by Semantic Contexts of Scenes
Some studies have revealed that contexts of scenes (e.g., "home," "office," and "cooking") are advantageous for sound event detection (SED). Mobile devices and sensing technologies give useful information on scenes for SED without the use of acoustic signals. However, conventional methods can employ pre-defined contexts in inference stages but not undefined contexts. This is because one-hot representations of pre-defined scenes are exploited as prior contexts for such conventional methods. To alleviate this problem, we propose scene-informed SED where pre-defined scene-agnostic contexts are available for more accurate SED. In the proposed method, pre-trained large-scale language models are utilized, which enables SED models to employ unseen semantic contexts of scenes in inference stages. Moreover, we investigated the extent to which the semantic representation of scene contexts is useful for SED. Experimental results performed with TUT Sound Events 2016/2017 and TUT Acoustic Scenes 2016/2017 datasets show that the proposed method improves micro and macro F-scores by 4.34 and 3.13 percentage points compared with conventional Conformer- and CNN--BiGRU-based SED, respectively.
- Open Access
Sound Event Detection Based on Curriculum Learning Considering Learning Difficulty of Events
In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot effectively exploit the difference between the two types of events. All time frames of sound events that do not occur in an acoustic scene are easily regarded as inactive in the scene, that is, the events are easy-to-train. The time frames of the events that are present in a scene must be classified as active in addition to inactive in the acoustic scene, that is, the events are difficult-to-train. To take advantage of the training difficulty, we apply curriculum learning into SED, where models are trained from easy- to difficult-to-train events. To utilize the curriculum learning, we propose a new objective function for SED, wherein the events are trained from easy- to difficult-to-train events. Experimental results show that the F-score of the proposed method is improved by 10.09 percentage points compared with that of the conventional binary cross entropy-based SED.
Open AccessSound Event Detection Based on Curriculum Learning Considering Learning Difficulty of Events
In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot effectively exploit the difference between the two types of events. All time frames of sound events that do not occur in an acoustic scene are easily regarded as inactive in the scene, that is, the events are easy-to-train. The time frames of the events that are present in a scene must be classified as active in addition to inactive in the acoustic scene, that is, the events are difficult-to-train. To take advantage of the training difficulty, we apply curriculum learning into SED, where models are trained from easy- to difficult-to-train events. To utilize the curriculum learning, we propose a new objective function for SED, wherein the events are trained from easy- to difficult-to-train events. Experimental results show that the F-score of the proposed method is improved by 10.09 percentage points compared with that of the conventional binary cross entropy-based SED.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Characteristics Study of Dance-charts on Rhythm-based Video Games
This paper studies the characteristics of dancecharts on rhythm-based video games while clustering the dancecharts with the track features. In the opinion of expert players, it is considered that the difficulty level of the rhythm-based games depends on multiple features for the song and chart. The difficulty levels for dance games has not well been studied though it has been already done for other genres of games. This paper designed the track features for dance games, which would be varied depending on characteristics of the track. Moreover, we conducted a dance-charts clustering by using the k-means method with the designed features. As a result of the clustering, it was confirmed that the clusters were composed mostly based on the step frequency and the complexity of rhythm. Also, it was found that the scores with the extremely characteristic features were separated from other scores and clustered as one class with themselves. The discussion in this paper indicated a possibility for the objective evaluation of the dance-charts.
- 1 August 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Characteristics Study of Dance-charts on Rhythm-based Video Games
This paper studies the characteristics of dancecharts on rhythm-based video games while clustering the dancecharts with the track features. In the opinion of expert players, it is considered that the difficulty level of the rhythm-based games depends on multiple features for the song and chart. The difficulty levels for dance games has not well been studied though it has been already done for other genres of games. This paper designed the track features for dance games, which would be varied depending on characteristics of the track. Moreover, we conducted a dance-charts clustering by using the k-means method with the designed features. As a result of the clustering, it was confirmed that the clusters were composed mostly based on the step frequency and the complexity of rhythm. Also, it was found that the scores with the extremely characteristic features were separated from other scores and clustered as one class with themselves. The discussion in this paper indicated a possibility for the objective evaluation of the dance-charts.
- 30 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 26 (9) , 1559-1569
Single-Channel Speech Enhancement With Phase Reconstruction Based on Phase Distortion Averaging
Speech enhancement has been widely investigated for several decades, but by modifying only the amplitude spectrum of a speech signal, ignoring the phase spectrum, which has been regarded as an unimportant feature. However, it was recently reported that the phase spectrum plays an important role in speech quality and intelligibility. In this paper, we propose a phase reconstruction method based on harmonic enhancement using the fundamental frequency and phase distortion feature. This feature is known to show fluctuations in the phase spectrum with respect to time and frequency. We estimate the speech phase spectrum by considering the relationship between harmonic phase spectra. Experimental evaluations indicate that the proposed phase reconstruction method improves speech quality in various noisy environments.
- 30 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 26 (9) , 1559-1569
Single-Channel Speech Enhancement With Phase Reconstruction Based on Phase Distortion Averaging
Speech enhancement has been widely investigated for several decades, but by modifying only the amplitude spectrum of a speech signal, ignoring the phase spectrum, which has been regarded as an unimportant feature. However, it was recently reported that the phase spectrum plays an important role in speech quality and intelligibility. In this paper, we propose a phase reconstruction method based on harmonic enhancement using the fundamental frequency and phase distortion feature. This feature is known to show fluctuations in the phase spectrum with respect to time and frequency. We estimate the speech phase spectrum by considering the relationship between harmonic phase spectra. Experimental evaluations indicate that the proposed phase reconstruction method improves speech quality in various noisy environments.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1316-1321
Online sound structure analysis based on generative model of acoustic feature sequences
We propose a method for the online sound structure analysis based on a Bayesian generative model of acoustic feature sequences, with which the hierarchical generative process of the sound clip, acoustic topic, acoustic word, and acoustic feature is assumed. In this model, it is assumed that sound clips are organized based on the combination of latent acoustic topics, and each acoustic topic is represented by a Gaussian mixture model (GMM) over an acoustic feature space, where the components of the GMM correspond to acoustic words. Since the conventional batch algorithm for learning this model requires a huge amount of calculation, it is difficult to analyze the massive amount of sound data. Moreover, the batch algorithm does not allow us to analyze the sequentially obtained data. Our variational Bayes-based online algorithm for this generative model can analyze the structure of sounds sound clip by sound clip. The experimental results show that the proposed online algorithm can reduce the calculation cost by about 90% and estimate the posterior distributions as efficiently as the conventional batch algorithm.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1316-1321
Online sound structure analysis based on generative model of acoustic feature sequences
We propose a method for the online sound structure analysis based on a Bayesian generative model of acoustic feature sequences, with which the hierarchical generative process of the sound clip, acoustic topic, acoustic word, and acoustic feature is assumed. In this model, it is assumed that sound clips are organized based on the combination of latent acoustic topics, and each acoustic topic is represented by a Gaussian mixture model (GMM) over an acoustic feature space, where the components of the GMM correspond to acoustic words. Since the conventional batch algorithm for learning this model requires a huge amount of calculation, it is difficult to analyze the massive amount of sound data. Moreover, the batch algorithm does not allow us to analyze the sequentially obtained data. Our variational Bayes-based online algorithm for this generative model can analyze the structure of sounds sound clip by sound clip. The experimental results show that the proposed online algorithm can reduce the calculation cost by about 90% and estimate the posterior distributions as efficiently as the conventional batch algorithm.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Estimation of speech recognition performance in noisy and reverberant environments using PESQ score and acoustic parameters
The automatic speech recognition (ASR) performance is degraded in noisy and reverberant environments. Although various techniques against degradation of the ASR performance have been proposed, it is difficult to properly apply them in evaluation environments with unknown noisy and reverberant conditions. It is possible to properly apply these techniques for improving the ASR performance if we can estimate the relationship between the ASR performance and degradation factors including both noise and reverberation. In this study, we here propose new noisy and reverberant criteria which are referred as “Noisy and Reverberant Speech Recognition with the PESQ and the D n (NRSR-PD n )”. We first designed the “NRSR-PD n ” using the relationships among the D value, the PESQ score, and the ASR performance. We then estimated the ASR performance with the designed criteria “NRSR-PD n ” in evaluation experiments. Experimental evaluations demonstrated that our proposed criteria make the well suited for robustly estimating the ASR performance in noisy and reverberant environments.
- 1 October 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Estimation of speech recognition performance in noisy and reverberant environments using PESQ score and acoustic parameters
The automatic speech recognition (ASR) performance is degraded in noisy and reverberant environments. Although various techniques against degradation of the ASR performance have been proposed, it is difficult to properly apply them in evaluation environments with unknown noisy and reverberant conditions. It is possible to properly apply these techniques for improving the ASR performance if we can estimate the relationship between the ASR performance and degradation factors including both noise and reverberation. In this study, we here propose new noisy and reverberant criteria which are referred as “Noisy and Reverberant Speech Recognition with the PESQ and the D n (NRSR-PD n )”. We first designed the “NRSR-PD n ” using the relationships among the D value, the PESQ score, and the ASR performance. We then estimated the ASR performance with the designed criteria “NRSR-PD n ” in evaluation experiments. Experimental evaluations demonstrated that our proposed criteria make the well suited for robustly estimating the ASR performance in noisy and reverberant environments.
- 1 July 2010
- Published by Springer Nature in Welding in the World
- Vol. 54 (7-8) , R182-R188
Difference between ASTM E1290 and BS 7448 CTOD Estimation Procedures
- 1 July 2010
- Published by Springer Nature in Welding in the World
- Vol. 54 (7-8) , R182-R188
Difference between ASTM E1290 and BS 7448 CTOD Estimation Procedures
- 16 September 2002
- Published by International Speech Communication Association
- p. 1181-1184
Extraction of important sentences using F0 information for speech summarization
- 16 September 2002
- Published by International Speech Communication Association
- p. 1181-1184
Extraction of important sentences using F0 information for speech summarization