REVIEW 7 cited by
Earnings-22: A Practical Benchmark for Accents in the Wild
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Modern automatic speech recognition (ASR) systems have achieved superhuman Word Error Rate (WER) on many common corpora despite lacking adequate performance on speech in the wild. Beyond that, there is a lack of real-world, accented corpora to properly benchmark academic and commercial models. To ensure this type of speech is represented in ASR benchmarking, we present Earnings-22, a 125 file, 119 hour corpus of English-language earnings calls gathered from global companies. We run a comparison across 4 commercial models showing the variation in performance when taking country of origin into consideration. Looking at hypothesis transcriptions, we explore errors common to all ASR systems tested. By examining Individual Word Error Rate (IWER), we find that key speech features impact model performance more for certain accents than others. Earnings-22 provides a free-to-use benchmark of real-world, accented audio to bridge academic and industrial research.
Forward citations
Cited by 7 Pith papers
-
A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff
Synset-based reconstruction and synonymous variational inference are claimed to derive the distributional divergence in RDP and unify it with classical rate-distortion theory.
-
Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding
Multi-negative contrastive decoding with noise, silence and temporal-shift negatives cuts Whisper long-form WER by up to 24.3 pp while remaining faster than beam search.
-
Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models
A benchmark of eight post-training quantization methods on Whisper and Moonshine edge speech models across seven datasets, finding 8-bit is safe and 3-bit weights are viable for larger models with advanced methods like SpQR.
-
FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation
A hierarchical Q-Former compresses speech to about 1.67 tokens/sec, enabling hour-long audio processing with near-linear memory scaling and competitive benchmark scores.
-
Adapting Whisper for Streaming Speech Recognition via Two-Pass Decoding
A U2-style two-pass adaptation with an 8,000-token CTC branch turns Whisper into a streaming ASR model that runs on CPUs in real time.
-
Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance
Earnings25 releases ~500 hours of 2025 earnings-call audio with aligned transcripts, speaker/industry metadata, and reproducible Whisper and Parakeet-TDT baselines.
-
ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition
A distillation method that decays teacher loss then applies self-distillation yields a Whisper-derived ASR model with 5x lower latency and slightly better average WER only on in-domain noisy datasets.
Discussion (0). Sign in to comment.