相关论文: Achieving Timestamp Prediction While Recognizing w…

In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of…

Estimating confidence scores for recognition results is a classic task in ASR field and of vital importance for kinds of downstream tasks and training strategies. Previous end-to-end~(E2E) based confidence estimation models (CEM) predict…

The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanism creates a smooth and monotonic mapping from acoustic features to target tokens, achieving…

Continuous integrate-and-fire (CIF) based models, which use a soft and monotonic alignment mechanism, have been well applied in non-autoregressive (NAR) speech recognition with competitive performance compared with other NAR methods.…

Integrate-and-Fire Time Encoding Machine (IF-TEM) is a power-efficient asynchronous sampler that converts analog signals into non-uniform time-domain samples. Adaptive IF-TEM (AIF-TEM) improves this machine by adapting its process to the…

RNN-T models are widely used in ASR, which rely on the RNN-T loss to achieve length alignment between input audio and target sequence. However, the implementation complexity and the alignment-based optimization target of RNN-T loss lead to…

We introduce a data-driven approach for enabling word-level timestamp prediction in the Canary model. Accurate timestamp information is crucial for a variety of downstream tasks such as speech content retrieval and timed subtitles. While…

An integrate-and-fire time-encoding machine (IF-TEM) is an effective asynchronous sampler that translates amplitude information into non-uniform time sequences. In this work, we propose a novel Adaptive IF-TEM (AIF-TEM) approach. This…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by…

Joint modeling of multi-speaker ASR and speaker diarization has recently shown promising results in speaker-attributed automatic speech recognition (SA-ASR).Although being able to obtain state-of-the-art (SOTA) performance, most of the…

Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference,…

A digital finite impulse response (FIR) filter design is fully synthesizable, thanks to the mature CAD support of digital circuitry. On the contrary, analog mixed-signal (AMS) filter design is mostly a manual process, including architecture…

Forced alignment (FA) plays a key role in speech research through the automatic time alignment of speech signals with corresponding text transcriptions. Despite the move towards end-to-end architectures for speech technology, FA is still…

High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose a self-supervised domain adaptation method, based upon an iterative pseudo-forced alignment algorithm. The produced alignments are…

Recently, end-to-end models have been widely used in automatic speech recognition (ASR) systems. Two of the most representative approaches are connectionist temporal classification (CTC) and attention-based encoder-decoder (AED) models.…

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist…

This work aims to introduce a heuristic timestep-adaptive algorithm for Computational Fluid Dynamics (CFD) and Fluid-Structure Interaction (FSI) problems where the flow is dominated by the pressure. In such scenarios, many time-adaptive…

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal…