A comparative study of noise reduction techniques for automatic speech recognition systems

Garg, Kanika; Jain, Goonjan

doi:10.1109/icacci.2016.7732361

Cited by 16 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sound recognition has been applied to many applications including intelligent noise-canceling systems [20,46] and assistive devices for deaf and hard-of-hearing people [10,35]. While recent advances in deep neural networks have also significantly improved the state-ofthe-art performance of generic sound recognition [21,25], it still has difficulties in accuracy and task diversity, and user adaptation is often required to meet real-world demands.…”

Section: Sound Recognition and Annotationmentioning

confidence: 99%

Investigating audio data visualization for interactive sound recognition

Ishibashi

Nakao

Sugano

2020

Proceedings of the 25th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Interactive machine learning techniques have a great potential to personalize media recognition models for each individual user by letting them browse and annotate a large amount of training data. However, graphical user interfaces (GUIs) for interactive machine learning have been mainly investigated in image and text recognition scenarios, not in other data modalities such as sound. In a scenario where users browse a large amount of audio files to search and annotate target samples corresponding to their own sound recognition classes, it is difficult for them to easily navigate through the overall sample structure due to the non-visual nature of audio data. In this work, we investigate the design issue for interactive sound recognition by comparing different visualization techniques ranging from audio spectrograms to deep learning-based audio-to-image retrieval. Based on an analysis of the user study, we clarify the advantages and disadvantages of audio visualization techniques, and provide design implications for interactive sound recognition GUIs using a massive amount of audio samples. CCS CONCEPTS • Human-centered computing → Human computer interaction (HCI).

show abstract

Section: Sound Recognition and Annotationmentioning

confidence: 99%

Investigating audio data visualization for interactive sound recognition

Ishibashi

Nakao

Sugano

2020

Proceedings of the 25th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…In Step1, the ensemble technique is used to create 3-copies of the input speech signal by using three different noise reduction filters: Spectral Subtraction, Wiener filter, and Gammatone filter. These three filters were chosen because they are considered the best in removing noise from the signal [14]. The generated copies are similar but non-identical.…”

Section: Proposed Techniquementioning

confidence: 99%

“…(Filter 3) The Gammatone filter was designed to express the performance of the human auditory system and to improve the automatic speech recognition system [14,24]. It is a linear filter that uses logarithmically spaced defined in the impulse response time, which is measured by the product of a sinusoidal tone and gamma distribution.…”

Section: Proposed Techniquementioning

confidence: 99%

“…For instance, identifying the speech of a person in a silent room is much easier than identifying the speech in a noisy environment. Thus, several researchers reported that ASR accuracy is still low for a degraded speech signal [12][13][14]. The effect of different noise types on speech recognition varies significantly according to the source of the noise [15].…”

Section: Introductionmentioning

confidence: 99%

“…The noise types may result from hundreds of sources, such as microphone quality, speaker characteristics, background sounds, and dialect differences [4]. Furthermore, various types of noise give different levels of errors, making it difficult to implement a filter technique for each type of noise or training the ASR on them [14]. Thus, the more efficient is the design of a general technique that can be more accurate for speech recognition in the presence of noise.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An ensemble technique for speech recognition in noisy environments

Habeeb

Fadhil

Jurn

et al. 2020

IJEECS

View full text Add to dashboard Cite

<span>Automatic speech recognition (ASR) is a technology that allows a computer and mobile device to recognize and translate spoken language into text. ASR systems often produce poor accuracy for the noisy speech signal. Therefore, this research proposed an ensemble technique that does not rely on a single filter for perfect noise reduction but incorporates information from multiple noise reduction filters to improve the final ASR accuracy. The main factor of this technique is the generation of K-copies of the speech signal using three noise reduction filters. The speech features of these copies differ slightly in order to extract different texts from them when processed by the ASR system. Thus, the best among these texts can be elected as final ASR output. The ensemble technique was compared with three related current noise reduction techniques in terms of CER and WER. The test results were encouraging and showed a relatively decreased by 16.61% and 11.54% on CER and WER compared with the best current technique. ASR field will benefit from the contribution of this research to increase the recognition accuracy of a human speech in the presence of background noise.</span>

show abstract

G-Cocktail: An Algorithm to Address Cocktail Party Problem of Gujarati Language Using Cat Boost

Gupta

Singh²,

Singh

2022

Wireless Pers Commun

View full text Add to dashboard Cite

The pandemic caused due to COVID-19, has seen things going online. People tired of typing prefer to give voice commands. Most of the voice based applications and devices are not prepared to handle the native languages. Moreover, in a party environment it is difficult to identify a voice command as there are many speakers. The proposed work addresses the Cocktail party problem of Indian language, Gujarati. The voice response systems like, Siri, Alexa, Google Assistant as of now work on single voice command. The proposed algorithm G-Cocktail would help these applications to identify command given in Gujarati even from a mixed voice signal. Benchmark Dataset is taken from Microsoft and Linguistic Data Consortium for Indian Languages(LDC-IL) comprising single words and phrases. G-Cocktail utilizes the power of CatBoost algorithm to classify and identify the voice. Voice print of the entire sound files is created using Pitch, and Mel Frequency Cepstral Coefficients (MFCC). Seventy percent of the voice prints are used to train the network and thirty percent for testing. The proposed work is tested and compared with K-means, Naïve Bayes, and LightGBM.

show abstract

A comparative study of noise reduction techniques for automatic speech recognition systems

Cited by 16 publications

References 10 publications

Investigating audio data visualization for interactive sound recognition

Investigating audio data visualization for interactive sound recognition

An ensemble technique for speech recognition in noisy environments

G-Cocktail: An Algorithm to Address Cocktail Party Problem of Gujarati Language Using Cat Boost

Contact Info

Product

Resources

About