Related papers: Dolphin-CN-Dialect: Where Chinese Dialects Matter

Deep learning has shown promising performance on various machine learning tasks. Nevertheless, the uninterpretability of deep learning models severely restricts the usage domains that require feature explanations, such as text correction.…

With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…

Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usability. Despite its importance, the integration of streaming…

In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length…

In recent years, dock-less shared bikes have been widely spread across many cities in China and facilitate people's lives. However, at the same time, it also raises many problems about dock-less shared bike management due to the mismatching…

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage…

The fifth Dialog State Tracking Challenge (DSTC5) introduces a new cross-language dialog state tracking scenario, where the participants are asked to build their trackers based on the English training corpus, while evaluating them with the…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…

Recently, online end-to-end ASR has gained increasing attention. However, the performance of online systems still lags far behind that of offline systems, with a large gap in quality of recognition. For specific scenarios, we can trade-off…

The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units.…

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Speech enhancement has benefited from the success of deep learning in terms of intelligibility and perceptual quality. Conventional time-frequency (TF) domain methods focus on predicting TF-masks or speech spectrum, via a naive convolution…

Neurosymbolic learning enables the integration of symbolic reasoning with deep learning but faces significant challenges in scaling to complex symbolic programs, large datasets, or both. We introduce DOLPHIN, a framework that tackles these…

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible…

Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper, we introduce a new layer normalization technique called…

Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased…