Perceptual wavelet decomposition for speech segmentation

Ziółko, Mariusz; Gałka, Jakub; Ziółko, Bartosz; Drwiega, Tomasz

doi:10.21437/interspeech.2010-614

Cited by 10 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNN-based structures have demonstrated superior effectiveness compared to alternative architectures employed in the Arabic ASR system [51]. Various well-known techniques such as Principal Component Analysis (PCA) [52], Independent Component Analysis (ICA) [53], Wavelet Analysis [54], and Linear Discriminant Analysis (LDA) [55] have been employed for deriving speech characteristics from acoustic waveform. Among these methods, PCA is commonly used to find patterns in input data.…”

Section: B Recent Advances In Asr Technologiesmentioning

confidence: 99%

Arabic Speech Recognition: Advancement and Challenges

Rahman,

Kabir,

Mridha

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Speech recognition is a captivating process that revolutionizes human-computer interactions, allowing us to interact and control machines through spoken commands. The foundation of speech recognition lies in understanding a given language's linguistic and textual characteristics. Although automatic speech recognition (ASR) systems flawlessly convert speech into text for various international languages, their implementation for Arabic remains inadequate. In this research, we diligently explore the current state of Arabic ASR systems and unveil the challenges encountered during their development. We categorize these challenges into two groups: those specific to the Arabic language and those that are more general. Additionally, we propose strategies to overcome these obstacles and emphasize the need for ASR architectures tailored to the Arabic language's unique grammatical and phonetic structure. In addition, we provide a comprehensive and explicit description of various feature extraction methods, language models, and acoustic models utilized in the Arabic ASR system.

show abstract

Section: B Recent Advances In Asr Technologiesmentioning

confidence: 99%

Arabic Speech Recognition: Advancement and Challenges

Rahman,

Kabir,

Mridha

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This often includes orthographic or phonetic transcription data, which contributes in parallel to the speech or training algorithms. Methods falling into this category encompass techniques using Hidden Markov Models (HMMs) [24], Dynamic Time Warping (DTW) [25], or Artificial Neural Networks (ANNs) [26,27].…”

Section: ) Automatic Segmentationmentioning

confidence: 99%

“…A substantial body of research adopts aided segmentation techniques. For example, B Ziółko [25] employed Discrete Wavelet Transform (DWT) analysis using the Wavelet Method to identify the start and end of phonemes. Kamarauskas [28] utilized perceptron and backpropagation artificial neural networks to recognize distinctive phonemes, with backpropagation showing lower recognition error rates but requiring longer training times.…”

Section: ) Automatic Segmentationmentioning

confidence: 99%

Improving Automatic Forced Alignment for Phoneme Segmentation in Quranic Recitation

Alqadasi,

Zeki,

Sunar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Segmentation plays a crucial role in speech processing applications, where high accuracy is essential. The quest for improved accuracy in automatic segmentation, particularly in the context of the Arabic language, has garnered substantial attention. However, the differences between Qur'an recitation and normal Arabic speech, especially with regard to intonation rules affecting the lengthening of long vowels, pose challenges in segmentation especially for Qur'an recitation. This research endeavors to address these challenges by delving into the domain of automatic segmentation for Qur'an recitation recognition. The proposed scheme employs a hidden Markov models (HMMs) forced alignment algorithm. To enhance the precision of segmentation, several refinements have been introduced, with a primary emphasis on the phonetic model of the Qur'an and Tajweed, particularly the intricate rules governing elongation. These enhancements encompass the adaptation of an acoustic model tailored for Qur'anic recitation as preprocessing and culminate in the development of an algorithm aimed at refining forced alignment based on the phonetic nuances of the Qur'an. These enhancements are seamlessly integrated as post-processing components for the classic HMM-based forced alignment. The research utilizes a comprehensive database featuring recordings from 100 renowned Qur'an reciters, encompassing the recitation of 21 Qur'anic verses (Ayat). Additionally, 30 reciters were asked to record the same verses, incorporating various recitation speed patterns. To facilitate the evaluation process, a Random sample of the Qur'anic database was manually segmented, comprised 21 Ayats, totaling 19,800 words, with 89 unique words (14 verses x 3 recitation levels: fast, slow and normal x 6 readers). The outcomes of this study manifest notable advancements in the alignment of long vowels within Qur'an recitation, all while maintaining the precise alignment of vowels and consonants. Objective comparisons between the proposed automatic methods and manual segmentation were conducted to ascertain the superior approach. The findings affirm that the classic forced alignment method produces satisfactory outcomes when employed on verses lacking long vowels. However, its performance diminishes when confronted with verses containing long vowels. Therefore, the test samples were categorized into three groups based on the presence of long vowels, resulting in a Correct Classification Rate (CCR) that ranged from 6% to 57%, contingent on whether the verse includes long vowels or not. The average CCR across all test samples was 23%. In contrast, the proposed algorithm significantly enhances audio segmentation. It achieved CCR values ranging from 16% to 70% within the same database categories, with an average CCR of 45% across all test samples. This marks a notable advancement of 22% in segmented speech accuracy, particularly within a 30 ms tolerance, for verses containing long vowels.

show abstract

“…The methods for boundary detection can be based on using bidirectional LSTM networks, 39,40 wavelet analysis, [42][43][44] graph-based structural analysis, 45 rules describing the power spectrum 46 or formants 47 and various features extracted from the spectrogram, for example, visual features 48,49 or auditory attention features. 50 The methods for boundary detection also have a relevant application in the task of segmentation with orthographic or phonetic transcription provided, where they can be used as additional boundary correction procedures.…”

Section: Related Workmentioning

confidence: 99%

“…The methods for boundary detection can be based on using bidirectional LSTM networks, 39,40 wavelet analysis, 42‐44 graph‐based structural analysis, 45 rules describing the power spectrum 46 or formants 47 and various features extracted from the spectrogram, for example, visual features 48,49 or auditory attention features 50 …”

Section: Introductionmentioning

confidence: 99%

Using LSTM neural networks for cross‐lingual phonetic speech segmentation with an iterative correction procedure

Hanzlíček,

Matoušek,

Vít

2023

Computational Intelligence

View full text Add to dashboard Cite

This article describes experiments on speech segmentation using long short‐term memory recurrent neural networks. The main part of the paper deals with multi‐lingual and cross‐lingual segmentation, that is, it is performed on a language different from the one on which the model was trained. The experimental data involves large Czech, English, German, and Russian speech corpora designated for speech synthesis. For optimal multi‐lingual modeling, a compact phonetic alphabet was proposed by sharing and clustering phones of particular languages. Many experiments were performed exploring various experimental conditions and data combinations. We proposed a simple procedure that iteratively adapts the inaccurate default model to the new voice/language. The segmentation accuracy was evaluated by comparison with reference segmentation created by a well‐tuned hidden Markov model‐based framework with additional manual corrections. The resulting segmentation was also employed in a unit selection text‐to‐speech system. The generated speech quality was compared with the reference segmentation by a preference listening test.

show abstract

Perceptual wavelet decomposition for speech segmentation

Cited by 10 publications

References 7 publications

Arabic Speech Recognition: Advancement and Challenges

Arabic Speech Recognition: Advancement and Challenges

Improving Automatic Forced Alignment for Phoneme Segmentation in Quranic Recitation

Using LSTM neural networks for cross‐lingual phonetic speech segmentation with an iterative correction procedure

Contact Info

Product

Resources

About