Related papers: Dynamic Alignment Mask CTC: Improved Mask-CTC with…

Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing…

This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per…

Remote sensing change detection (RSCD) is a complex task, where changes often appear at different scales and orientations. Convolutional neural networks (CNNs) are good at capturing local spatial patterns but cannot model global semantics…

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile…

Phonetic speech transcription is crucial for fine-grained linguistic analysis and downstream speech applications. While Connectionist Temporal Classification (CTC) is a widely used approach for such tasks due to its efficiency, it often…

In this work, we address the Text-to-Speech (TTS) task by proposing a non-autoregressive architecture called EfficientTTS. Unlike the dominant non-autoregressive TTS models, which are trained with the need of external aligners, EfficientTTS…

This study (The work was accomplished during the internship in Tencent AI lab) addresses semi-supervised acoustic modeling, i.e. attaining high-level representations from unsupervised audio data and fine-tuning the parameters of pre-trained…

Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements…

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of…

In this work, we present a simple but effective method, CTCBERT, for advancing hidden-unit BERT (HuBERT). HuBERT applies a frame-level cross-entropy (CE) loss, which is similar to most acoustic model training. However, CTCBERT performs the…

This paper proposes a novel formulation of prototypical loss with mixup for speaker verification. Mixup is a simple yet efficient data augmentation technique that fabricates a weighted combination of random data point and label pairs for…

Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model rollouts. We introduce a feature-matching…

Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder…

Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motivated the development of Test-Time Adaptation (TTA) to improve…

In our previous work, we proposed a discriminative autoencoder (DcAE) for speech recognition. DcAE combines two training schemes into one. First, since DcAE aims to learn encoder-decoder mappings, the squared error between the reconstructed…

Lyrics alignment gained considerable attention in recent years. State-of-the-art systems either re-use established speech recognition toolkits, or design end-to-end solutions involving a Connectionist Temporal Classification (CTC) loss.…

In deep regression, capturing the relationship among continuous labels in feature space is a fundamental challenge that has attracted increasing interest. Addressing this issue can prevent models from converging to suboptimal solutions…

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters…

We study the problem of asymptotic consensus as it occurs in a wide range of applications in both man-made and natural systems. In particular, we study systems with directed communication graphs that may change over time. We recently…

Diffusion models have emerged as a promising approach for generating high-quality, high-dimensional images. Nevertheless, these models are hindered by their high computational cost and slow inference, partly due to the quadratic…