Noise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation

Obuchi, Yasunari; Takeda, Ryo; Togami, Masahito

doi:10.1250/ast.34.133

Cited by 4 publications

(4 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The latency of the proposed noise suppression was 50ms due to the ΔΔ feature calculation in Eq. (7). Memory usage was 1,168,347 bytes.…”

Section: Implementation On Dspmentioning

confidence: 99%

“…One [1]- [10] does not require pre-training, and the other [11]- [23] does. Well-known examples of the first type include spectral subtraction (SS) [1], Wiener filtering (WF) [2], minimum mean-square error short-time spectral amplitude (MMSE STSA) [3], [4], minimum meansquare error log-spectral amplitude (MMSE LSA) [5], [8], and optimally-modified log-spectral amplitude (OM-LSA) [6], [7]. Advanced Front-end (AFE) [9], [10] of ETSI (European Telecommunications Standards Institute), which applies WF in two stages, is particularly known for its high noise robustness, and it is often used for comparison in research studies.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Low-Complexity and Accurate Noise Suppression Based on an a Priori SNR Model for Robust Speech Recognition on Embedded Systems and Its Evaluation in a Car Environment

Tsujikawa

KAJIKAWA

2023

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

In this paper, we propose a low-complexity and accurate noise suppression based on an a priori SNR (Speech to Noise Ratio) model for greater robustness w.r.t. short-term noise-fluctuation. The a priori SNR, the ratio of speech spectra and noise spectra in the spectral domain, represents the difference between speech features and noise features in the feature domain, including the mel-cepstral domain and the logarithmic power spectral domain. This is because logarithmic operations are used for domain conversions. Therefore, an a priori SNR model can easily be expressed in terms of the difference between the speech model and the noise model, which are modeled by the Gaussian mixture models, and it can be generated with low computational cost. By using a priori SNRs accurately estimated on the basis of an a priori SNR model, it is possible to calculate accurate coefficients of noise suppression filters taking into account the variance of noise, without serious increase in computational cost over that of a conventional model-based Wiener filter (MBW). We have conducted in-car speech recognition evaluation using the CENSREC-2 database, and a comparison of the proposed method with a conventional MBW showed that the recognition error rate for all noise environments was reduced by 9%, and that, notably, that for audio-noise environments was reduced by 11%. We show that the proposed method can be processed with low levels of computational and memory resources through implementation on a digital signal processor.

show abstract

“…The latency of the proposed noise suppression was 50ms due to the ΔΔ feature calculation in Eq. (7). Memory usage was 1,168,347 bytes.…”

Section: Implementation On Dspmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Low-Complexity and Accurate Noise Suppression Based on an a Priori SNR Model for Robust Speech Recognition on Embedded Systems and Its Evaluation in a Car Environment

Tsujikawa

KAJIKAWA

2023

IEICE Trans. Fundamentals

View full text Add to dashboard Cite

show abstract

“…As a speech enhancement algorithm for our system, we implemented bidirectional OM-LSA (BOMLSA) speech estimator [23]. OM-LSA [24] is an extension of FFT-based a priori SNR estimator of Ephraim and Malah [25].…”

Section: Speech Enhancement and Merging Asr Outputsmentioning

confidence: 99%

“…Furthermore, we made HN-E (high noise, enhanced) and LN-E (low noise, enhanced) speech samples by applying a speech enhancement algorithm to HN-R and LN-R, respectively. We used the bidirectional OMLSA algorithm [23] for the enhancement.…”

Section: Interview-based Collection Of Experimental Datasetmentioning

confidence: 99%

In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer

Homma

Obuchi

Shima

et al. 2018

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

For voice-enabled car navigation systems that use a multipurpose cloud speech recognition service (cloud ASR), utterance classification that is robust against speech recognition errors is needed to realize a user-friendly voice interface. The purpose of this study is to improve the accuracy of utterance classification for voice-enabled car navigation systems when inputs to a classifier are error-prone speech recognition results obtained from a cloud ASR. The role of utterance classification is to predict which car navigation function a user wants to execute from a spontaneous utterance. A cloud ASR causes speech recognition errors due to the noises that occur when traveling in a car, and the errors degrade the accuracy of utterance classification. There are many methods for reducing the number of speech recognition errors by modifying the inside of a speech recognizer. However, application developers cannot apply these methods to cloud ASRs because they cannot customize the ASRs. In this paper, we propose a system for improving the accuracy of utterance classification by modifying both speech-signal inputs to a cloud ASR and recognizedsentence outputs from an ASR. First, our system performs speech enhancement on a user's utterance and then sends both enhanced and non-enhanced speech signals to a cloud ASR. Speech recognition results from both speech signals are merged to reduce the number of recognition errors. Second, to reduce that of utterance classification errors, we propose a data augmentation method, which we call "optimal doping," where not only accurate transcriptions but also error-prone recognized sentences are added to training data. An evaluation with real user utterances spoken to car navigation products showed that our system reduces the number of utterance classification errors by 54% from a baseline condition. Finally, we propose a semi-automatic upgrading approach for classifiers to benefit from the improved performance of cloud ASRs.

show abstract

Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection

Fujita

Takashima

Homma

et al. 2015

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

View full text Add to dashboard Cite

Noise suppression method for preprocessor of time-lag speech recognition system based on bidirectional optimally modified log spectral amplitude estimation

Cited by 4 publications

References 18 publications

Low-Complexity and Accurate Noise Suppression Based on an a Priori SNR Model for Robust Speech Recognition on Embedded Systems and Its Evaluation in a Car Environment

Low-Complexity and Accurate Noise Suppression Based on an a Priori SNR Model for Robust Speech Recognition on Embedded Systems and Its Evaluation in a Car Environment

In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer

Unified ASR system using LGM-based source separation, noise-robust feature extraction, and word hypothesis selection

Contact Info

Product

Resources

About