Oral English Speech Recognition Based on Enhanced Temporal Convolutional Network

Wu, Hao; Sangaiah, Arun Kumar

doi:10.32604/iasc.2021.016457

Cited by 9 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, s n , s p } first. Then the duration predictor outputs the window length [2, 1, 4, 3] and window position [1, 2.5, 5, 8.5], so the added window length is [4,3,6,5], and four speech segments can be obtained. The first segment is {s p , s 1 , s 2 , s 3 }, and the second segment is {s 2 , s 3 , s 4 }, and so on.…”

Section: Audio Spectrum Extractmentioning

confidence: 99%

See 1 more Smart Citation

A New Speech Encoder Based on Dynamic Framing Approach

Liu¹,

Yang²,

Zhou³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Latent information is difficult to get from the text in speech synthesis. Studies show that features from speech can get more information to help text encoding. In the field of speech encoding, a lot of work has been conducted on two aspects. The first aspect is to encode speech frame by frame. The second aspect is to encode the whole speech to a vector. But the scale in these aspects is fixed. So, encoding speech with an adjustable scale for more latent information is worthy of investigation. But current alignment approaches only support frame-by-frame encoding and speech-to-vector encoding. It remains a challenge to propose a new alignment approach to support adjustable scale speech encoding. This paper presents the dynamic speech encoder with a new alignment approach in conjunction with frame-by-frame encoding and speech-to-vector encoding. The speech feature from our model achieves three functions. First, the speech feature can reconstruct the origin speech while the length of the speech feature is equal to the text length. Second, our model can get text embedding from speech, and the encoded speech feature is similar to the text embedding result. Finally, it can transfer the style of synthesis speech and make it more similar to the given reference speech.

show abstract

Section: Audio Spectrum Extractmentioning

confidence: 99%

“…There are two main ways in previous research to get prosodic features from speech. The two ways are frame-by-frame encoding [5,6] and speech-to-vector encoding [7,8]. Frame-by-frame encoding encodes each speech frame to a vector, and it can get more detailed features from speech.…”

Section: Introductionmentioning

confidence: 99%

A New Speech Encoder Based on Dynamic Framing Approach

Liu¹,

Yang²,

Zhou³

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

show abstract

“…The parameters of the neural network part are updated layer-by-layer and frame-by-frame according to the back-propagation algorithm. When CTC decodes the output, the output sequence must be optimized to obtain the final label sequence [12]. This study adopted the Best path decoding algorithm, assuming that the probability maximum path π and the probability maximum label l * have a one-to-one correspondence, meaning that the many-to-one mapping B is degenerated into a one-to-one mapping relationship and each frame is accepted by the algorithm [13].…”

Section: The Connectionist Temporal Classification-convolutional Neur...mentioning

confidence: 99%

Improving Speech Enhancement Framework via Deep Learning

Hsiao¹,

Sung²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Speech plays an extremely important role in social activities. Many individuals suffer from a "speech barrier," which limits their communication with others. In this study, an improved speech recognition method is proposed that addresses the needs of speech-impaired and deaf individuals. A basic improved connectionist temporal classification convolutional neural network (CTC-CNN) architecture acoustic model was constructed by combining a speech database with a deep neural network. Acoustic sensors were used to convert the collected voice signals into text or corresponding voice signals to improve communication. The method can be extended to modern artificial intelligence techniques, with multiple applications such as meeting minutes, medical reports, and verbatim records for cars, sales, etc. For experiments, a modified CTC-CNN was used to train an acoustic model, which showed better performance than the earlier common algorithms. Thus a CTC-CNN baseline acoustic model was constructed and optimized, which reduced the error rate to about 18% and improved the accuracy rate.

show abstract

“…The calculation of the forward-backward algorithm is as follows: For the input sequence x and the label sequence l with the time sequence length T, the extended label sequence is l , and the length of the extended label sequence is |l | = 2|l| + 1, defining the first t. The forward probability of outputting the extended label at the sth position at the moment is α(t,s), and the posterior probability calculation formula of the label sequence is shown in Eq. ( 5) [12].…”

Section: Core Idea Of Ctcmentioning

confidence: 99%

“…The loss function of CTC is defined as the negative log probability of the label sequence on the training set S. Then, the loss function (x) output of each sample is given by Eq. (12).…”

Section: Core Idea Of Ctcmentioning

confidence: 99%

Speech Recognition via CTC-CNN Model

Sung,

Kang,

Hsiao

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In the speech recognition system, the acoustic model is an important underlying model, and its accuracy directly affects the performance of the entire system. This paper introduces the construction and training process of the acoustic model in detail and studies the Connectionist temporal classification (CTC) algorithm, which plays an important role in the end-to-end framework, established a convolutional neural network (CNN) combined with an acoustic model of Connectionist temporal classification to improve the accuracy of speech recognition. This study uses a sound sensor, ReSpeaker Mic Array v2.0.1, to convert the collected speech signals into text or corresponding speech signals to improve communication and reduce noise and hardware interference. The baseline acoustic model in this study faces challenges such as long training time, high error rate, and a certain degree of overfitting. The model is trained through continuous design and improvement of the relevant parameters of the acoustic model, and finally the performance is selected according to the evaluation index. Excellent model, which reduces the error rate to about 18%, thus improving the accuracy rate. Finally, comparative verification was carried out from the selection of acoustic feature parameters, the selection of modeling units, and the speaker's speech rate, which further verified the excellent performance of the CTCCNN_5 + BN + Residual model structure. In terms of experiments, to train and verify the CTC-CNN baseline acoustic model, this study uses THCHS-30 and ST-CMDS speech data sets as training data sets, and after 54 epochs of training, the word error rate of the acoustic model training set is 31%, the word error rate of the test set is stable at about 43%. This experiment also considers the surrounding environmental noise. Under the noise level of 80∼90 dB, the accuracy rate is 88.18%, which is the worst performance among all levels. In contrast, at 40-60 dB, the accuracy was as high as 97.33% due to less noise pollution.

show abstract

Oral English Speech Recognition Based on Enhanced Temporal Convolutional Network

Cited by 9 publications

References 21 publications

A New Speech Encoder Based on Dynamic Framing Approach

A New Speech Encoder Based on Dynamic Framing Approach

Improving Speech Enhancement Framework via Deep Learning

Speech Recognition via CTC-CNN Model

Contact Info

Product

Resources

About