LibriSpeech
PulseAugur coverage of LibriSpeech — every cluster mentioning LibriSpeech across labs, papers, and developer communities, ranked by signal.
10 day(s) with sentiment data
-
User seeks help implementing Calm TTS paper, facing voice cloning issues
A user is seeking assistance with implementing the Calm text-to-speech model described in a research paper. They have encountered difficulties in replicating the model's performance, experiencing issues with generating …
-
New neural diarization model excels on low-resource Nepali-Hindi speech
Researchers have developed a new approach to speaker diarization, the process of identifying who spoke when in an audio recording, specifically for low-resource languages like Nepali-Hindi. They trained two neural netwo…
-
Hugging Face launches FFASR Leaderboard for real-world ASR benchmarking
Hugging Face and Treble Technologies have launched the FFASR Leaderboard, an open, community-driven benchmark for evaluating Automatic Speech Recognition (ASR) models in realistic far-field acoustic conditions. This new…
-
New ASR method InterAligner improves training stability and reduces errors
Researchers have developed a new method called InterAligner to improve the training stability and performance of Aligner-Encoder based Automatic Speech Recognition (ASR) models. This approach introduces an intermediate …
-
New research reveals CTC limitations in speech recognition, highlights linguistic model benefits
A new research paper explores the limitations of Connectionist Temporal Classification (CTC) in speech recognition systems. The study found that CTC's internal scoring methods struggle to improve accuracy beyond basic g…
-
New research tackles ASR challenges with synthetic speech, LLM optimization, and failure reduction
Researchers are developing advanced techniques to improve Automatic Speech Recognition (ASR) systems, particularly for challenging scenarios like code-switching and real-time applications. One paper proposes a code-mixi…
-
New NAR-MBR Decoding Boosts Speech Recognition Speed and Accuracy
Researchers have developed a new non-autoregressive decoding framework for speech recognition, termed NAR-MBR decoding. This method aims to improve the speed of speech recognition by generating output tokens in parallel…
-
Speech models compressed using parameter clustering
Researchers have developed a new method for compressing speech foundation models without requiring additional data or retraining. This approach utilizes channelwise clustering with k-means to achieve parameter compressi…
-
New model uses continuous space for speech recognition and translation
Researchers have introduced ELF-S2T, a novel approach to speech-to-text systems that operates in a continuous latent space rather than discrete text tokens. This model, built on the Embedded Language Flows (ELF) backbon…
-
New ASR methods tackle compute scaling and multilingual evaluation
Researchers are developing new methods to improve automatic speech recognition (ASR) systems. One approach, LARM, uses a depth-conditioned looped Transformer to allow for adjustable test-time computation, achieving perf…
-
Neuromorphic Mamba models boost speech recognition efficiency
Researchers have developed new neuromorphic versions of the Mamba model for more efficient automatic speech recognition (ASR). By incorporating spiking and event-driven neural network techniques, they achieved significa…
-
Quantization study enables smaller, more accurate Whisper-small ASR
A new study published on arXiv evaluates various post-training quantization (PTQ) techniques for the Whisper-small automatic speech recognition model. The research, which tested libraries like PyTorch, Optimum-Quanto, H…
-
New framework uses calculus to optimize ASR vocabulary size
Researchers have developed a calculus-based framework to determine the optimal vocabulary size for end-to-end Automatic Speech Recognition (ASR) systems. Unlike traditional hybrid ASR, end-to-end systems derive their vo…
-
New research explores text-only data for faster encoder-dominated speech recognition models
This paper introduces novel methods for enhancing speech recognition models by leveraging text-only data. The research focuses on encoder-dominated architectures, demonstrating that a larger encoder paired with a smalle…