相关论文: Custom Data Augmentation for low resource ASR usin…

We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for…

Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…

Semi-supervised training (SST) is a common approach to leverage untranscribed/unlabeled speech data to improve automatic speech recognition performance in low-resource languages. However, if the available unlabeled speech is mismatched to…

Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several…

Hearable devices, equipped with one or more microphones, are commonly used for speech communication. Here, we consider the scenario where a hearable is used to capture the user's own voice in a noisy environment. In this scenario, own voice…

Data augmentation via voice conversion (VC) has been successfully applied to low-resource expressive text-to-speech (TTS) when only neutral data for the target speaker are available. Although the quality of VC is crucial for this approach,…

Data augmentation is a technique to generate new training data based on existing data. We evaluate the simple and cost-effective method of concatenating the original data examples to build new training instances. Continued training with…

Text-to-speech (TTS) systems are an important component in voice-based e-commerce applications. These applications include end-to-end voice assistant and customer experience (CX) voice bot. Code-mixed TTS is also relevant in these…

We propose a semi-supervised learning method for building end-to-end rich transcription-style automatic speech recognition (RT-ASR) systems from small-scale rich transcription-style and large-scale common transcription-style datasets. In…

Despite the significant progress in end-to-end (E2E) automatic speech recognition (ASR), E2E ASR for low resourced code-switching (CS) speech has not been well studied. In this work, we describe an E2E ASR pipeline for the recognition of CS…

Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification,…

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating…

Attention-based contextual biasing approaches have shown significant improvements in the recognition of generic and/or personal rare-words in End-to-End Automatic Speech Recognition (E2E ASR) systems like neural transducers. These…

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…

We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…

This study investigates the efficacy of data augmentation techniques for low-resource automatic speech recognition (ASR), focusing on two endangered Austronesian languages, Amis and Seediq. Recognizing the potential of self-supervised…