Speech recognition using neural networks

Tsenov, Georgi; Mladenov, Valeri

doi:10.1109/neurel.2010.5644073

Cited by 12 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results could be then compared with the literature [20]. In the future work a recognition performance of consonants and words [12] should be evaluated. The authors are going to develop a mobile devices equipped with a microphone and digital video camera that will incorporate the presented methods.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Vowel recognition of patients after total laryngectomy using Mel Frequency Cepstral Coefficients and mouth contour

Pietruch

Grzanka

2010

J Autom Control

View full text Add to dashboard Cite

The paper addresses a problem of isolated vowels recognition in patients following total laryngectomy. The visual and acoustic speech modalities were separately incorporated in the machine learning algorithms. The authors used the Mel Frequency Cepstral Coefficients as acoustic descriptors of a speech signal. A lip contour was extracted from a video signal of the speaking faces using OpenCV software library. In a vowels recognition procedure the three types of classifiers were used for comparison purposes: Artificial Neural Networks, Support Vector Machines and Naive Bayes. The highest recognition rate was evaluated using Support Vector Machines. For a group of the laryngectomees having a different quality of speech the authors achieved 75% for acoustic and 40% for visual recognition performances. The authors obtained higher recognition rate than in a previous research where 10 cross-sectional areas of a vocal tract were estimated. Using presented image processing algorithm the visual features can be extracted automatically from a video signal

show abstract

Section: Discussionmentioning

confidence: 99%

“…This speech recognition approach was already applied for laryngectomees [10]. As it was shown the MFCC parameters are also capable for all vowels [11] and whole words [12] recognition. Therefore, the method can be used by authors in the future work.…”

Section: B Multimodal Speech Signal Analysismentioning

confidence: 99%

Vowel recognition of patients after total laryngectomy using Mel Frequency Cepstral Coefficients and mouth contour

Pietruch

Grzanka

2010

J Autom Control

View full text Add to dashboard Cite

show abstract

“…Speech (or voice) recognition systems essentially computer programs (with auxiliary peripherals) those hear, record and identify voice commands and relevant speeches of users. Working principles and some more details regarding such systems can be found elsewhere [8,9]. They mainly have two main types, as text-dependent and text-independent systems.…”

Section: Voice Recognitionmentioning

confidence: 99%

A Proposal on Initial Remote User Enrollment for IVR-based Voice Authentication Systems

Cabuk¹,

Şenocak²,

Demir³

2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

In the last decade, Interactive Voice Response (IVR) systems gained popularity among customer care, phone banking and many other commercial services. It helps to reduce conversation and dialing overheads, guides customers and automates call forwardings. On the other hand, many sensitive phone and online services, including banking operations and e-government applications, require strict and accurate user/customer authentication schemes. Although not being preferred so far, with regards to the recent developments on the voice recognition techniques, IVR emerges as a brilliant solution for authentication, too. When using IVR for voice authentication, all potential users must be enrolled and voiceprints (records) must be collected prior to start of the service. However, for scenarios where users are located in geographically distant places, it is very hard, if not impossible, to gather all the users in enrollment offices. So, this initial enrollment process should better be done remotely. In this study, we come up with a systematic method that allows institutions to enroll their users and record their voiceprints remotely, without compromising reliability of further authentication.

show abstract

“…The feature extraction plays a very important role in speech identification. As a result of irregularities in human speech features, human speech can be sensibly interpreted using frequency-time interpretations such as a spectrogram [20].…”

Section: Feature Extractionmentioning

confidence: 99%

A Novel Approach to Stuttered Speech Correction

Alim

Rashid

Sediono

et al. 2016

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

Stuttered speech is a dysfluency rich speech, more prevalent in males than females. It has been associated with insufficient air pressure or poor articulation, even though the root causes are more complex. The primary features include prolonged speech and repetitive speech, while some of its secondary features include, anxiety, fear, and shame. This study used LPC analysis and synthesis algorithms to reconstruct the stuttered speech. The results were evaluated using cepstral distance, Itakura-Saito distance, mean square error, and likelihood ratio. These measures implied perfect speech reconstruction quality. ASR was used for further testing, and the results showed that all the reconstructed speech samples were perfectly recognized while only three samples of the original speech were perfectly recognized. Keywords: stuttered speech, speech reconstruction, LPC analysis, LPC synthesis, objective quality measure AbstrakShuttered speech adalah speech yang kaya dysfluency, lebih banyak terjadi pada laki-laki daripada perempuan. Ini terkait dengan tekanan udara yang tidak cukup atau artikulasi yang buruk, meskipun akar penyebabnya lebih kompleks. Fitur utama termasuk speech yang berkepanjangan dan berulangulang, sementara beberapa fitur sekunder meliputi, kecemasan, ketakutan, dan rasa malu. Penelitian ini menggunakan LPC analysis dan synthesis algoritma untuk merekonstruksi stuttered speech. Hasil dievaluasi menggunakan jarak cepstral, jarak Itakura-Saito, mean square error, dan rasio likelihood. Langkah-langkah ini terkandung kualitas speech reconstruction yang sempurna. ASR digunakan untuk pengujian lebih lanjut, dan hasilnya menunjukkan bahwa semua sampel speech yang terekonstruksi dikenali dengan sempurna sementara hanya tiga sampel dari speech asli dikenali dengan sempurna.

show abstract

Speech recognition using neural networks

Cited by 12 publications

References 5 publications

Vowel recognition of patients after total laryngectomy using Mel Frequency Cepstral Coefficients and mouth contour

Vowel recognition of patients after total laryngectomy using Mel Frequency Cepstral Coefficients and mouth contour

A Proposal on Initial Remote User Enrollment for IVR-based Voice Authentication Systems

A Novel Approach to Stuttered Speech Correction

Contact Info

Product

Resources

About