Related papers: Voice Conversion Can Improve ASR in Very Low-Resou…

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…

In this paper, we propose a self-training approach for automatic speech recognition (ASR) for low-resource settings. While self-training approaches have been extensively developed and evaluated for high-resource languages such as English,…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

Low resource automatic speech recognition (ASR) is a useful but thorny task, since deep learning ASR models usually need huge amounts of training data. The existing models mostly established a bottleneck (BN) layer by pre-training on a…

We present a simple approach to improve direct speech-to-text translation (ST) when the source language is low-resource: we pre-train the model on a high-resource automatic speech recognition (ASR) task, and then fine-tune its parameters…

Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…

Speaker identity is one of the important characteristics of human speech. In voice conversion, we change the speaker identity from one to another, while keeping the linguistic content unchanged. Voice conversion involves multiple speech…

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…

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to…

This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST). We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and…

Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are…

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…

Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by converting between source and target acoustic features. Our…

Voice conversion technologies have been greatly improved in recent years with the help of deep learning, but their capabilities of producing natural sounding utterances in different conditions remain unclear. In this paper, we gave a…

Voice conversion (VC) is a task that transforms voice from target audio to source without losing linguistic contents, it is challenging especially when source and target speakers are unseen during training (zero-shot VC). Previous…

Speech enhancement improves speech quality and promotes the performance of various downstream tasks. However, most current speech enhancement work was mainly devoted to improving the performance of downstream automatic speech recognition…

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…

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data…

This paper introduces Taco-VC, a novel architecture for voice conversion based on Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large number of…

Recently, large pre-trained multilingual speech models have shown potential in scaling Automatic Speech Recognition (ASR) to many low-resource languages. Some of these models employ language adapters in their formulation, which helps to…