A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging

Fujimoto, Mitoshi

doi:10.1093/ietisy/e89-d.3.922

Cited by 13 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The speech recognition system used in VoiceTra consisted of a frontend, which performed noise suppression using particle filtering [13] and acoustic analysis, and a backend, which performed large vocabulary continuous speech recognition (LVCSR) using ATRASR [14].…”

Section: Multilingual Speech Recognitionmentioning

confidence: 99%

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Matsuda

Hayashi

Ashikari

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis study introduces large-scale field experiments of VoiceTra, which is the world's first speech-to-speech multilingual translation application for smart phones. In the study, approximately 10 million input utterances were collected since the experiments commenced. The usage of collected data was analyzed and discussed. The study has several important contributions. First, it explains system configuration, communication protocol between clients and servers, and details of multilingual automatic speech recognition, multilingual machine translation, and multilingual speech synthesis subsystems. Second, it demonstrates the effects of mid-term system updates using collected data to improve an acoustic model, a language model, and a dictionary. Third, it analyzes system usage.

show abstract

Section: Multilingual Speech Recognitionmentioning

confidence: 99%

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Matsuda

Hayashi

Ashikari

et al. 2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…For analyzing the speech data, we employ an HMM-based speech recognizer (ATRASR 11 developed by Itoh et al), which is high-precision speech recognition software on noise environments 12 to obtain the phoneme segmentation. The phoneme segmentation result is further converted to the viseme segmentation using a phoneme-viseme mapping table by the simple table lookup The supported languages are Japanese and English.…”

Section: Viseme Segmentation Servermentioning

confidence: 99%

Efficient lip‐synch tool for 3D cartoon animation

Kawamoto

Yotsukura²,

Anjyo³

et al. 2008

Computer Animation & Virtual

View full text Add to dashboard Cite

We propose a set of algorithms to efficiently make speech animation for 3D cartoon characters. Our prototype system is based on blendshapes, a linear interpolation technique, which is widely used in facial animation practice. In our system, a few base target shapes of the character, prerecorded voice, and its transcription are required as input. We describe a simple technique that amplifies the target shapes from few inputs using a generic database of viseme mouth shapes. We also introduce additional lip-synch editing parameters that allow designers to quickly tune the lip movements. Based on these, we implement our prototype system as a Maya plug-in. The demonstration movies created with this system illustrate well the practicality of our approach.

show abstract

“…Our proposed method used an extended Kalman particle filter with residual sampling and MCMC as did [6]. To introduce it to MM-NS, the distributions of noise models are used as priors for particles.…”

Section: Noise Suppression Proceduresmentioning

confidence: 99%

“…The Gaussian Mixture Model (GMM) based Minimum Mean-Squared Error (MMSE) method [4] assumes that input noise is stationary but fluctuating. Recently, noise suppression research has focused on non-stationary noise, including a sequential EM approach [5], a particle filtering approach [6], and so on. Since these methods usually assume that only one kind of noise signal exists, applying them to noisy speech that includes many kinds of noise signals is difficult.…”

Section: Introductionmentioning

confidence: 99%

Multi-Model Noise Suppression using Particle Filtering

Jitsuhiro

Toriyama

Kiyokawa

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

We propose a noise suppression method based on multi-model compositions using particle filtering. In real environments, input speech for speech recognition includes many kinds of noise signals. For such noisy speech, we previously proposed Multi-model Noise Suppression (MM-NS) that uses many kinds of noise models and their compositions obtained from training data. However, since MM-NS only uses the static property of noise models, handling unknown noise distributions is difficult. We introduce a particle filter into MM-NS. The distributions of noise models are used as prior distributions of particle filtering to increase the accuracy of the estimation of noise signals for input data. We evaluated this method using the E-Nightingale task, which contains voice memoranda spoken by nurses during actual work at hospitals. The proposed method outperformed the original MM-NS.

show abstract

A Non-stationary Noise Suppression Method Based on Particle Filtering and Polyak Averaging

Cited by 13 publications

References 0 publications

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Development of the “VoiceTra” Multi-Lingual Speech Translation System

Efficient lip‐synch tool for 3D cartoon animation

Multi-Model Noise Suppression using Particle Filtering

Contact Info

Product

Resources

About