Related papers: Deferred NAM: Low-latency Top-K Context Injection …
Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the…
Automated audio captioning aims to describe audio data with captions using natural language. Existing methods often employ an encoder-decoder structure, where the attention-based decoder (e.g., Transformer decoder) is widely used and…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Transformer-based neural speech processing has achieved state-of-the-art performance. Since speech audio signals are known to be highly compressible, here we seek to accelerate neural speech transcription by time-domain signal…
Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…
Neural attention (NA) has become a key component of sequence-to-sequence models that yield state-of-the-art performance in as hard tasks as abstractive document summarization (ADS) and video captioning (VC). NA mechanisms perform inference…
Achieving super-human performance in recognizing human speech has been a goal for several decades, as researchers have worked on increasingly challenging tasks. In the 1990's it was discovered, that conversational speech between two humans…
End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…
Streaming speech recognition architectures are employed for low-latency, real-time applications. Such architectures are often characterized by their causality. Causal architectures emit tokens at each frame, relying only on current and past…
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its…
Contextual biasing (CB) improves automatic speech recognition for rare and unseen phrases. Recent studies have introduced dynamic vocabulary, which represents context phrases as expandable tokens in autoregressive (AR) models. This method…
Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on…
Convolutional frontends are a typical choice for Transformer-based automatic speech recognition to preprocess the spectrogram, reduce its sequence length, and combine local information in time and frequency similarly. However, the width and…
Transfer learning from high-resource languages is known to be an efficient way to improve end-to-end automatic speech recognition (ASR) for low-resource languages. Pre-trained or jointly trained encoder-decoder models, however, do not share…
Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…
Non-autoregressive automatic speech recognition (ASR) has become a mainstream of ASR modeling because of its fast decoding speed and satisfactory result. To further boost the performance, relaxing the conditional independence assumption and…
Targeted sentiment classification aims at determining the sentimental tendency towards specific targets. Most of the previous approaches model context and target words with RNN and attention. However, RNNs are difficult to parallelize and…
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve this…
Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…
This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning.…