An introduction to voice search

Wang, Ye-Yi; Yu, Dong; Ju, Yun-Cheng; Acero, Alex

doi:10.1109/msp.2008.918411

Cited by 56 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is similar to how cepstral coefficients are calculated in MFCC. We could convert between Mel frequency (m) and frequency (f ) in hertz by using Equations (2) and (3).…”

Section: Mel Frequency Warpingmentioning

confidence: 99%

“…Various applications based on speech recognition are already facilitating humankind in different tasks. Using voice search in different applications [3,4], users can search for anything using voice commands instead of using a keyboard for search. There are many examples of such applications like query search engines, driving directions, search for hotels and restaurants, and search for products on e-commerce websites.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Noise Robustness in Speech Command Recognition by Noise Augmentation of Training Data

Pervaiz

Hussain

Israr

et al. 2020

Sensors

View full text Add to dashboard Cite

The advent of new devices, technology, machine learning techniques, and the availability of free large speech corpora results in rapid and accurate speech recognition. In the last two decades, extensive research has been initiated by researchers and different organizations to experiment with new techniques and their applications in speech processing systems. There are several speech command based applications in the area of robotics, IoT, ubiquitous computing, and different human-computer interfaces. Various researchers have worked on enhancing the efficiency of speech command based systems and used the speech command dataset. However, none of them catered to noise in the same. Noise is one of the major challenges in any speech recognition system, as real-time noise is a very versatile and unavoidable factor that affects the performance of speech recognition systems, particularly those that have not learned the noise efficiently. We thoroughly analyse the latest trends in speech recognition and evaluate the speech command dataset on different machine learning based and deep learning based techniques. A novel technique is proposed for noise robustness by augmenting noise in training data. Our proposed technique is tested on clean and noisy data along with locally generated data and achieves much better results than existing state-of-the-art techniques, thus setting a new benchmark.

show abstract

“…This is similar to how cepstral coefficients are calculated in MFCC. We could convert between Mel frequency (m) and frequency (f ) in hertz by using Equations (2) and (3).…”

Section: Mel Frequency Warpingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Incorporating Noise Robustness in Speech Command Recognition by Noise Augmentation of Training Data

Pervaiz

Hussain

Israr

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…1. Voice search is the technology intended to provide users with the information they request with a spoken query [84]. The information requested often exists in a structured or unstructured large database (e.g., the Web being a huge, unstructured database).…”

Section: Voice Searchmentioning

confidence: 99%

“…That is, the full SLT system can be viewed as ASR and MT subsystems in tandem (e.g., [14], [39], [62], [66], [83], and [96]). As another example, a voice search system also recognizes the input utterance as ''noisy'' text first, and then feeds it as a query to a subsequent information retrieval (IR) system, returning a list of documents ranked by their relevance to the query (e.g., [29], [30], and [84]). As a further example, a spoken language understanding (SLU) system again recognizes the input utterance first, and then feeds the noisy transcription to a natural language understanding (NLU) system.…”

Section: Introductionmentioning

confidence: 99%