Related papers: Phoneme-Based Contextualization for Cross-Lingual …

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

Context-aware neural machine translation aims to use the document-level context to improve translation quality. However, not all words in the context are helpful. The irrelevant or trivial words may bring some noise and distract the model…

Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicons developed by experts. This poses a two-fold problem.…

Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the…

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Although end-to-end (E2E) trainable automatic speech recognition (ASR) has shown great success by jointly learning acoustic and linguistic information, it still suffers from the effect of domain shifts, thus limiting potential applications.…

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However,…

Classic embedded feature selection algorithms are often divided in two large groups: tree-based algorithms and lasso variants. Both approaches are focused in different aspects: while the tree-based algorithms provide a clear explanation…

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the…

Recent works have shown that modelling raw waveform directly from text in an end-to-end (E2E) fashion produces more natural-sounding speech than traditional neural text-to-speech (TTS) systems based on a cascade or two-stage approach.…

We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide…

Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related…

Multilingual speech recognition has drawn significant attention as an effective way to compensate data scarcity for low-resource languages. End-to-end (e2e) modelling is preferred over conventional hybrid systems, mainly because of no…

We report on adaptation of multilingual end-to-end speech recognition models trained on as many as 100 languages. Our findings shed light on the relative importance of similarity between the target and pretraining languages along the…

We propose a cross-lingual neural codec language model, VALL-E X, for cross-lingual speech synthesis. Specifically, we extend VALL-E and train a multi-lingual conditional codec language model to predict the acoustic token sequences of the…

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially…

This study presents a novel zero-shot user-defined keyword spotting model that utilizes the audio-phoneme relationship of the keyword to improve performance. Unlike the previous approach that estimates at utterance level, we use both…

Self-supervised speech models can be trained to efficiently recognize spoken words in naturalistic, noisy environments. However, we do not understand the types of linguistic representations these models use to accomplish this task. To…

End-to-end automatic speech recognition suffers from adaptation to unknown target domain speech despite being trained with a large amount of paired audio--text data. Recent studies estimate a linguistic bias of the model as the internal…

Mixture-of-experts based acoustic models with dynamic routing mechanisms have proved promising results for speech recognition. The design principle of router architecture is important for the large model capacity and high computational…