KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset

Mussakhojayeva, Saida; Janaliyeva, Aigerim; Mirzakhmetov, Almas; Khassanov, Yerbolat; Varol, Hüseyin Atakan

doi:10.21437/interspeech.2021-2124

Cited by 16 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to convert the text response from ChatGPT to speech, we used the gTTS (Google Text-to-Speech) library [16] for the English language and the Kazakh TTS model [17] for the Kazakh language. The gTTS is an interface to Google Translate's Text-to-Speech API.…”

Section: Text-to-speech (Tts)mentioning

confidence: 99%

ChatGPT for Visually Impaired and Blind

Kuzdeuov¹,

Nurgaliyev²,

Varol³

2023

Preprint

View full text Add to dashboard Cite

<p>According to the World Health Organization (WHO), more than hundreds of million people have some type of visual disability today. Vision impairment has a personal impact with lifelong consequences because more than 80\% of our perception, cognition, learning, and daily activities are mediated through vision. As a result, visually impaired and blind people stagnate at work and in education due to inaccessible technologies. In this regard, we present a speech-based assistive system for visually impaired and blind people to interact with ChatGPT. The system employs automatic speech recognition (ASR), text-to-speech (TTS), and a messenger bot (Telegram) to enable a natural interface to ChatGPT for people with visual disabilities. Our preliminary experiments showed the feasibility of the proposed system as an assistive technology. We have made the source code publicly available at https://github.com/IS2AI/telegram-bot-chatgpt to stimulate the development of assistive systems for the visually impaired and blind.</p>

show abstract

Section: Text-to-speech (Tts)mentioning

confidence: 99%

ChatGPT for Visually Impaired and Blind

Kuzdeuov¹,

Nurgaliyev²,

Varol³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Next, the generated caption text was converted into audio, using a text-to-speech model. In our study, we utilized the KazakhTTS model [25] to convert Kazakh text to speech. Finally, the generated audio was played through the user's headphones.…”

Section: Model Deploymentmentioning

confidence: 99%

Image Captioning for the Visually Impaired and Blind: A Recipe for Low-Resource Languages

Arystanbekov¹,

Kuzdeuov²,

Nurgaliyev³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Visually impaired and blind people often face a range of socioeconomic problems that can make it difficult for them to live independently and participate fully in society. Advances in machine learning pave new venues to implement assistive devices for the visually impaired and blind. In this work, we combined image captioning and text-to-speech technologies to create an assistive device for the visually impaired and blind. Our system can provide the user with descriptive auditory feedback in the Kazakh language on a scene acquired in real-time by a head-mounted camera. The image captioning model for the Kazakh language provided satisfactory results in both quantitative metrics and subjective evaluation. Finally, experiments with a visually unimpaired blindfolded participant demonstrated the feasibility of our approach.</p>

show abstract

“…To address the aforementioned problem, many datasets have been developed in less popular languages. For example, to advance speech processing research in Kazakhstan, researchers developed open-source Kazakh speech corpora for building speech recognition [17] and speech synthesis [24] applications. To enable speech research and increase accessibility of speech-enabled applications for illiterate users, Doumbouya et al [9] released 150 hours of transcribed audio data for West African languages.…”

Section: Related Workmentioning

confidence: 99%

USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments

Musaev¹,

Mussakhojayeva²,

Khujayorov³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present a freely available speech corpus for the Uzbek language and report preliminary automatic speech recognition (ASR) results using both the deep neural network hidden Markov model (DNN-HMM) and end-to-end (E2E) architectures. The Uzbek speech corpus (USC) comprises 958 different speakers with a total of 105 hours of transcribed audio recordings. To the best of our knowledge, this is the first open-source Uzbek speech corpus dedicated to the ASR task. To ensure high quality, the USC has been manually checked by native speakers. We first describe the design and development procedures of the USC, and then explain the conducted ASR experiments in detail. The experimental results demonstrate promising results for the applicability of the USC for ASR. Specifically, 18.1% and 17.4% word error rates were achieved on the validation and test sets, respectively. To enable experiment reproducibility, we share the USC dataset, pre-trained models, and training recipes in our GitHub repository 1 .

show abstract

KazakhTTS: An Open-Source Kazakh Text-to-Speech Synthesis Dataset

Cited by 16 publications

References 17 publications

ChatGPT for Visually Impaired and Blind

ChatGPT for Visually Impaired and Blind

Image Captioning for the Visually Impaired and Blind: A Recipe for Low-Resource Languages

USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments

Contact Info

Product

Resources

About