Related papers: Development of Automatic Speech Recognition for Ka…

In this study, we develop and assess new corpus selection and training methodologies to improve the effectiveness of Turkish language models. Specifically, we adapted Large Language Model generated datasets and translated English datasets…

This paper proposes a novel approach to an automatic estimation of three speaker traits from Arabic speech: gender, emotion, and dialect. After showing promising results on different text classification tasks, the multi-task learning (MTL)…

In this paper, we explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. First, we investigate how useful a pre-trained language model would be in a 2-step pipeline…

We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units. We model the output vocabulary of about 100,000 words directly…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

Recent success of the Tacotron speech synthesis architecture and its variants in producing natural sounding multi-speaker synthesized speech has raised the exciting possibility of replacing expensive, manually transcribed, domain-specific,…

Instruction tuning in low-resource languages remains underexplored due to limited text data, particularly in government and cultural domains. To address this, we introduce and open-source a large-scale (10,600 samples) instruction-following…

Incorporating information from other languages can improve the results of tasks in low-resource languages. A powerful method of building functional natural language processing systems for low-resource languages is to combine multilingual…

In this paper, we introduce the first large vocabulary speech recognition system (LVSR) for the Central Kurdish language, named Jira. The Kurdish language is an Indo-European language spoken by more than 30 million people in several…

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity,…

Today, transformer language models serve as a core component for majority of natural language processing tasks. Industrial application of such models requires minimization of computation time and memory footprint. Knowledge distillation is…

Building inclusive speech recognition systems is a crucial step towards developing technologies that speakers of all language varieties can use. Therefore, ASR systems must work for everybody independently of the way they speak. To…

Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a language of more than 450 million native speakers, by first…

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic…

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask:…

This technical report describes the methods and results of a three-week sprint to produce deployable speech recognition models for 31 under-served languages of the Common Voice project. We outline the preprocessing steps, hyperparameter…

To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2.0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al.,…

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…