相关论文: Collaborative Training of Acoustic Encoders for Sp…

This paper investigates efficient methods for utilizing text-only data to improve speech recognition, focusing on encoder-dominated models that facilitate faster recognition. We provide a comprehensive comparison of techniques to integrate…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to…

Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating…

We describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method incorporates four self-supervised and supervised subtasks for cross modality…

Multimodal representation learning has demonstrated remarkable potential in enabling models to process and integrate diverse data modalities, such as text and images, for improved understanding and performance. While the medical domain can…

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…

This paper proposes a novel approach to pre-train encoder-decoder sequence-to-sequence (seq2seq) model with unpaired speech and transcripts respectively. Our pre-training method is divided into two stages, named acoustic pre-trianing and…

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker…

Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into…

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency. To avoid redundant training and optimization efforts for individual models of different sizes,…

End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…

Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while…

Neural audio codecs have revolutionized audio processing by enabling speech tasks to be performed on highly compressed representations. Recent work has shown that speech separation can be achieved within these compressed domains, offering…

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. Two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic…

We propose a dynamic encoder transducer (DET) for on-device speech recognition. One DET model scales to multiple devices with different computation capacities without retraining or finetuning. To trading off accuracy and latency, DET…

Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…

This study introduces a novel training paradigm, audio difference learning, for improving audio captioning. The fundamental concept of the proposed learning method is to create a feature representation space that preserves the relationship…

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…