相关论文: Improving Code-Switching and Named Entity Recognit…

End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…

Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR…

End-to-End (E2E) automatic speech recognition (ASR) systems used in voice assistants often have difficulties recognizing infrequent words personalized to the user, such as names and places. Rare words often have non-trivial pronunciations,…

Improving end-to-end speech recognition by incorporating external text data has been a longstanding research topic. There has been a recent focus on training E2E ASR models that get the performance benefits of external text data without…

Automated Speech Recognition (ASR) is an interdisciplinary application of computer science and linguistics that enable us to derive the transcription from the uttered speech waveform. It finds several applications in Military like…

The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

Previous studies have confirmed that by augmenting acoustic features with the place/manner of articulatory features, the speech enhancement (SE) process can be guided to consider the broad phonetic properties of the input speech when…

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Dementia is a growing problem as our society ages, and detection methods are often invasive and expensive. Recent deep-learning techniques can offer a faster diagnosis and have shown promising results. However, they require large amounts of…

Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe deterrent to the inclusive adoption of ASR. In this work, we…

Recently Deep Transformer models have proven to be particularly powerful in language modeling tasks for ASR. Their high complexity, however, makes them very difficult to apply in the first (single) pass of an online system. Recent studies…

End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…

The challenge of fairness arises when Automatic Speech Recognition (ASR) systems do not perform equally well for all sub-groups of the population. In the past few years there have been many improvements in overall speech recognition…

Whispering is a distinct form of speech known for its soft, breathy, and hushed characteristics, often used for private communication. The acoustic characteristics of whispered speech differ substantially from normally phonated speech and…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

India is home to multiple languages, and training automatic speech recognition (ASR) systems for languages is challenging. Over time, each language has adopted words from other languages, such as English, leading to code-mixing. Most Indian…

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

Recently, an end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. It showed…

Text to speech (TTS) is widely used to synthesize personal voice for a target speaker, where a well-trained source TTS model is fine-tuned with few paired adaptation data (speech and its transcripts) on this target speaker. However, in many…