Related papers: Improving Uyghur ASR systems with decoders using m…

We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme…

High-quality and intelligible speech is essential to text-to-speech (TTS) model training, however, obtaining high-quality data for low-resource languages is challenging and expensive. Applying speech enhancement on Automatic Speech…

Visual cues, like lip motion, have been shown to improve the performance of Automatic Speech Recognition (ASR) systems in noisy environments. We propose LipGER (Lip Motion aided Generative Error Correction), a novel framework for leveraging…

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…

In this paper, we present UR-AIR system submission to the logical access (LA) and the speech deepfake (DF) tracks of the ASVspoof 2021 Challenge. The LA and DF tasks focus on synthetic speech detection (SSD), i.e. detecting text-to-speech…

Pashto is spoken by approximately 60--80 million people but has no published benchmarks for multilingual automatic speech recognition (ASR) on any shared public test set. This paper reports the first reproducible multi-model evaluation on…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network…

Vocoders, encoding speech signals into acoustic features and allowing for speech signal reconstruction from them, have been studied for decades. Recently, the rise of deep learning has particularly driven the development of neural vocoders…

Neural Architecture Representation Learning aims to transform network models into feature representations for predicting network attributes, playing a crucial role in deploying and designing networks for real-world applications. Recently,…

Contextual knowledge is essential for reducing speech recognition errors on high-valued long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) component that enables end-to-end ASR models to bias towards a…

Automatic Speech Recognition (ASR) for low-resource languages remains a challenging task due to limited training data. This paper introduces a comprehensive study exploring the effectiveness of Whisper, a pre-trained ASR model, for Northern…

Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…

Multilingual Automated Speech Recognition (ASR) systems allow for the joint training of data-rich and data-scarce languages in a single model. This enables data and parameter sharing across languages, which is especially beneficial for the…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

Automatic speech recognition (ASR) for African languages remains constrained by limited labeled data and the lack of systematic guidance on model selection, data scaling, and decoding strategies. Large pre-trained systems such as Whisper,…

This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the…

In sequence-to-sequence Transformer ASR, autoregressive (AR) models achieve strong accuracy but suffer from slow decoding, while non-autoregressive (NAR) models enable parallel decoding at the cost of degraded performance. We propose a…

Automated speech recognition coverage of the world's languages continues to expand. However, standard phoneme based systems require handcrafted lexicons that are difficult and expensive to obtain. To address this problem, we propose a…