word error rate
PulseAugur coverage of word error rate — every cluster mentioning word error rate across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
AssemblyAI details advanced speech recognition evaluation beyond WER
AssemblyAI has published a guide detailing advanced methods for evaluating speech-to-text models, moving beyond the traditional Word Error Rate (WER). The article highlights the limitations of WER, such as its inability…
-
Whisper model fine-tuned for robust Assamese speech recognition
Researchers have developed a fine-tuned version of the Whisper model to improve Automatic Speech Recognition (ASR) for the Assamese language. The fine-tuned model, trained on the Mozilla Common Voice 24.0-Assamese corpu…
-
AssemblyAI details best practices for production voice agents
AssemblyAI has published a series of blog posts detailing best practices for building production-ready voice agents. The articles emphasize the importance of robust telemetry and diagnostic pipelines to catch regression…
-
New RLHF framework improves Vietnamese translation of historical manuscripts
Researchers have developed a new multimodal Reinforcement Learning from Human Feedback (RLHF) framework to translate historical Han-Nom manuscripts into modern Vietnamese. This approach leverages both the visual informa…
-
New GRPO method boosts synthetic speech ASR performance
Researchers have developed a new method called Group Relative Policy Optimization (GRPO) to improve automatic speech recognition (ASR) models, particularly when trained on synthetic speech. This reinforcement learning a…
-
Qwen-ASR-1.7B adapted for multilingual two-speaker speech recognition · 2 sources tracked
Researchers have developed a system for the MLC-SLM 2026 Challenge that adapts the Qwen3-ASR-1.7B model for multilingual, two-speaker conversational speech. The system integrates a speaker diarization front end with the…
-
New pipeline enhances ASR robustness, cutting word error rate by 55%
Researchers have developed a novel dual-gate diagnostic pipeline to enhance the robustness of Automatic Speech Recognition (ASR) systems against adversarial and benign perturbations. This pipeline, featuring a Two-Sided…
-
AssemblyAI proposes Missed Entity Rate (MER) for medical transcription accuracy
AssemblyAI has introduced a new metric called Missed Entity Rate (MER) to better evaluate the accuracy of medical transcription services. Traditional Word Error Rate (WER) metrics treat all words equally, failing to dis…
-
New ASR techniques tackle phonetic errors and judge reliability
Researchers are developing advanced methods to improve Automatic Speech Recognition (ASR) systems, particularly for low-resource languages and to address specific types of errors. One approach, Error-Aware TF-IDF, uses …
-
New dataset and CRNN model advance Urdu handwritten text recognition
Researchers have introduced the Urdu Katib Handwritten Dataset (UKHD), the first offline dataset of historical Urdu handwritten text lines. This dataset aims to address the scarcity of resources for Urdu Handwritten Tex…
-
Neural audio codecs achieve smooth degradation down to 1.6 Hz
Researchers have investigated the degradation mechanisms in neural audio codecs operating at low frame rates, which are beneficial for autoregressive speech synthesis. Their study identified that a previously observed q…
-
New ASR Error Analysis Tool Breaks Script Barriers
Researchers have developed a new automated alignment mechanism designed to improve the analysis of Automatic Speech Recognition (ASR) errors, particularly for languages that do not use the Latin script. This method is l…
-
New paradigm improves ASR metrics by correlating errors with human perception
Researchers have introduced a new paradigm for evaluating automatic speech recognition (ASR) systems that aims to improve upon existing metrics like Word Error Rate (WER) and Character Error Rate (CER). The proposed met…
-
New LLMs unify audio and language processing for full-duplex and medical applications
Researchers have developed UAF, a novel unified audio front-end LLM designed for full-duplex speech interaction. This model integrates diverse audio front-end tasks like voice activity detection and turn-taking into a s…
-
Researchers introduce RAS, a new metric for reliable speech recognition systems
Researchers have introduced RAS, a new metric designed to evaluate the reliability of automatic speech recognition (ASR) systems. Unlike traditional metrics that focus solely on accuracy, RAS accounts for the system's c…
-
Gladia open-sources normalization library to improve STT evaluation accuracy
A new open-source library, gladia-normalization, has been released to address inconsistencies in evaluating speech-to-text (STT) models. The library standardizes transcripts before calculating Word Error Rate (WER), pre…