Related papers: SkiM: Skipping Memory LSTM for Low-Latency Real-Ti…

This paper presents our contribution to the 3rd CHiME Speech Separation and Recognition Challenge. Our system uses Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Networks (RNNs) for Single-channel Speech Enhancement (SSE).…

Convolutional Neural Network (CNN) or Long short-term memory (LSTM) based models with the input of spectrogram or waveforms are commonly used for deep learning based audio source separation. In this paper, we propose a Sliced…

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels. Recent advances have shown that joint ASR and SD models can learn to…

Recent years have witnessed Spiking Neural Networks (SNNs) gaining attention for their ultra-low energy consumption and high biological plausibility compared with traditional Artificial Neural Networks (ANNs). Despite their distinguished…

This paper describes a dataset and protocols for evaluating continuous speech separation algorithms. Most prior studies on speech separation use pre-segmented signals of artificially mixed speech utterances which are mostly \emph{fully}…

This paper describes a system that generates speaker-annotated transcripts of meetings by using a microphone array and a 360-degree camera. The hallmark of the system is its ability to handle overlapped speech, which has been an unsolved…

Large language Models (LLMs), though growing exceedingly powerful, comprises of orders of magnitude less neurons and synapses than the human brain. However, it requires significantly more power/energy to operate. In this work, we propose a…

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due…

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…

Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models suffer from very high computational and memory costs.…

The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features…

A new language model for speech recognition is presented. The model develops hidden hierarchical syntactic-like structure incrementally and uses it to extract meaningful information from the word history, thus complementing the locality of…

Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we…

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking process before responding. In contrast, humans typically engage…

Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs). However, while uniform-precision quantization is computationally efficient, it often compromises model performance. To address this, we…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…

In multi-session dialog system, it is essential to continuously update the memory as the session progresses. Simply accumulating memory can make it difficult to focus on the content of the conversation for inference due to the limited input…

Business sentiment analysis (BSA) is one of the significant and popular topics of natural language processing. It is one kind of sentiment analysis techniques for business purposes. Different categories of sentiment analysis techniques like…