Related papers: Phonemic and Graphemic Multilingual CTC Based Spee…

Recent publications on automatic-speech-recognition (ASR) have a strong focus on attention encoder-decoder (AED) architectures which tend to suffer from over-fitting in low resource scenarios. One solution to tackle this issue is to…

Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including end-to-end speech and handwritten character recognition. For…

Recent advances in synthetic speech quality have enabled us to train text-to-speech (TTS) systems by using synthetic corpora. However, merely increasing the amount of synthetic data is not always advantageous for improving training…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…

Mismatched data is a challenging problem for automatic speech recognition (ASR) systems. One of the most common techniques used to address mismatched data is multi-style training (MTR), a form of data augmentation that attempts to transform…

Performance degradation of an Automatic Speech Recognition (ASR) system is commonly observed when the test acoustic condition is different from training. Hence, it is essential to make ASR systems robust against various environmental…

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

For real-world deployment of automatic speech recognition (ASR), the system is desired to be capable of fast inference while relieving the requirement of computational resources. The recently proposed end-to-end ASR system based on…

Current automatic speech recognition (ASR) models are designed to be used across many languages and tasks without substantial changes. However, this broad language coverage hides performance gaps within languages, for example, across…

Developing Automatic Speech Recognition (ASR) for low-resource languages is a challenge due to the small amount of transcribed audio data. For many such languages, audio and text are available separately, but not audio with transcriptions.…

This paper proposes a method to relax the conditional independence assumption of connectionist temporal classification (CTC)-based automatic speech recognition (ASR) models. We train a CTC-based ASR model with auxiliary CTC losses in…

The kNN-CTC model has proven to be effective for monolingual automatic speech recognition (ASR). However, its direct application to multilingual scenarios like code-switching, presents challenges. Although there is potential for performance…

Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR) are important speech tasks, and require a large amount of text and speech pairs for model training. However, there are more than 6,000 languages in…

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual…

We propose data and knowledge-driven approaches for multilingual training of the automated speech recognition (ASR) system for a target language by pooling speech data from multiple source languages. Exploiting the acoustic similarities…

Speech Recognition (ASR) due to phoneme distortions and high variability. While self-supervised ASR models like Wav2Vec, HuBERT, and Whisper have shown promise, their effectiveness in dysarthric speech remains unclear. This study…