Related papers: Efficient Encoders for Streaming Sequence Tagging

Forward Error Correction (FEC) remains essential for protecting video streaming against packet loss, yet most real deployments still rely on static, coarse-grained configurations that cannot react to rapid shifts in loss rate, goodput, or…

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Traditional per-title encoding schemes aim to optimize encoding resolutions to deliver the highest perceptual quality for each representation. However, keeping the encoding time within an acceptable threshold for a smooth user experience is…

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…

OpenAI Whisper is a family of robust Automatic Speech Recognition (ASR) models trained on 680,000 hours of audio. However, its encoder-decoder architecture, trained with a sequence-to-sequence objective, lacks native support for streaming…

With streaming floating-point numbers being increasingly prevalent, effective and efficient compression of such data is critical. Compression schemes must be able to exploit the similarity, or smoothness, of consecutive numbers and must be…

Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection…

In conventional HTTP-based adaptive streaming (HAS), a video source is encoded at multiple levels of constant bitrate representations, and a client makes its representation selections according to the measured network bandwidth. While…

We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dynamically segments input streams to create compressed anchor…

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However,…

HTTP Adaptive Streaming (HAS) is nowadays a popular solution for multimedia delivery. The novelty of HAS lies in the possibility of continuously adapting the streaming session to current network conditions, facilitated by Adaptive Bitrate…

The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits…

A streaming style inference of encoder-decoder automatic speech recognition (ASR) system is important for reducing latency, which is essential for interactive use cases. To this end, we propose a novel blockwise synchronous decoding…

Streaming ASR with strict latency constraints is required in many speech recognition applications. In order to achieve the required latency, streaming ASR models sacrifice accuracy compared to non-streaming ASR models due to lack of future…

HTTP adaptive streaming (HAS) has emerged as a prevalent approach for over-the-top (OTT) video streaming services due to its ability to deliver a seamless user experience. A fundamental component of HAS is the bitrate ladder, which…

In HTTP adaptive live streaming applications, video segments are encoded at a fixed set of bitrate-resolution pairs known as bitrate ladder. Live encoders use the fastest available encoding configuration, referred to as preset, to ensure…

We introduce a novel network-adaptive algorithm that is suitable for alleviating network packet losses for low-latency interactive communications between a source and a destination. Our network-adaptive algorithm estimates in real-time the…

Adaptive bitrate streaming (ABR) over the HyperText Transfer Protocol (HTTP), which raises numerous delicate questions, is nowadays almost the only approach to video streaming. This paper presents elementary solutions to three key issues:…

An autoencoder-based codec employs quantization to turn its bottleneck layer activation into bitstrings, a process that hinders information flow between the encoder and decoder parts. To circumvent this issue, we employ additional skip…