SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.13352 · ICLR · 2022

ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition

Alexander Rush, Sanchit Gandhi, Patrick Von Platen

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 11 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
huggingface/open_asr_leaderboard pwc_unofficial 11 of 11
FunctionStatusWhere it lives
build_asr_keep_token_ids Ran huggingface/open_asr_leaderboard/ark_asr/run_eval.py
code served (permissive licence) · get_code("95565023b8f5c27e")
build_eos_token_ids Ran huggingface/open_asr_leaderboard/ark_asr/run_eval.py
code served (permissive licence) · get_code("34e38edcaaae0414")
normalize Ran huggingface/open_asr_leaderboard/benchmark_fitting/score_voxpopuli_ref_errors.py
code served (permissive licence) · get_code("251be1ea1d702e3c")
normalize_token_ids Ran huggingface/open_asr_leaderboard/ark_asr/run_eval.py
code served (permissive licence) · get_code("585c0c7f730e6d1f")
parse_hyp Ran huggingface/open_asr_leaderboard/nemo_asr/run_eval_salm.py
code served (permissive licence) · get_code("a41e5c4f1618068b")
resolve_device Ran huggingface/open_asr_leaderboard/audio8_asr/run_eval.py
code served (permissive licence) · get_code("e82aa9a9f589056d")
resolve_dtype Ran huggingface/open_asr_leaderboard/audio8_asr/run_eval.py
code served (permissive licence) · get_code("573d7aef30a8051e")
to_hub_id Ran huggingface/open_asr_leaderboard/normalizer/model_ids.py
code served (permissive licence) · get_code("20e94432951733ce")
to_hub_ids Ran huggingface/open_asr_leaderboard/normalizer/model_ids.py
code served (permissive licence) · get_code("bb9a452edf61892e")
transcribe Ran huggingface/open_asr_leaderboard/nemo_asr/run_eval_salm.py
code served (permissive licence) · get_code("465981d7412a5bb3")
unique_token_ids Ran huggingface/open_asr_leaderboard/audio8_asr/run_eval.py
code served (permissive licence) · get_code("288177fe23420283")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require dataset-specific tuning (audio filtering, punctuation removal and normalisation of casing), therefore assuming a-priori knowledge of both the audio and text distributions. This tuning requirement can lead to systems failing to generalise to other datasets and domains. To promote the development of multi-domain speech systems, we introduce the End-to-end Speech Benchmark (ESB) for evaluating the performance of a single automatic speech recognition (ASR) system across a broad set of speech datasets. Benchmarked systems must use the same data preand post-processing algorithm across datasets -assuming the audio and text data distributions are a-priori unknown. We compare a series of state-of-the-art (SoTA) end-to-end (E2E) systems on this benchmark, demonstrating how a single speech system can be applied and evaluated on a wide range of data distributions. We find E2E systems to be effective across datasets: in a fair comparison, E2E systems achieve within 2.6% of SoTA systems tuned to a specific dataset. Our analysis reveals that transcription artefacts, such as punctuation and casing, pose difficulties for ASR systems and should be included in evaluation. We believe E2E benchmarking over a range of datasets promotes the research of multi-domain speech recognition systems. ESB is available at https://huggingface.co/esb.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.13352")
get_code_for_paper("2210.13352")
have("2210.13352")

Connect an agent — have() is free.