RECORD
Acoustic Landmarks Contain More Information About the Phone String than Other Frames for Automatic Speech Recognition with Deep Neural Network Acoustic Model
Audio and Speech Processing · Submitted 27 Oct 2017
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim In this work, we conduct experiments on the TIMIT corpus, with both GMM and DNN based ASR systems and find that frames containing landmarks are more informative for ASR than others.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. Acoustic landmark theory exploits quantal non-linearities in the articulatory-acoustic and acoustic-perceptual relations to define landmark times at which the speech spectrum abruptly changes or reaches an extremum; frames overlapping landmarks have been demonstrated to be sufficient for speech perception. In this work, we conduct experiments on the TIMIT corpus, with both GMM and DNN based ASR systems and find that frames containing landmarks are more informative for ASR than others. We find that altering the level of emphasis on landmarks by re-weighting acoustic likelihood tends to reduce the phone error rate (PER). Furthermore, by leveraging the landmark as a heuristic, one of our hybrid DNN frame dropping strategies maintained a PER within 0.44% of optimal when scoring less than half (45.8% to be precise) of the frames. This hybrid strategy out-performs other non-heuristic-based methods and demonstrate the potential of landmarks for reducing computation.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. | background 0.95 | 0.03 | 0.05 | asserted 1.00 |
| s2 | Acoustic landmark theory exploits quantal non-linearities in the articulatory-acoustic and acoustic-perceptual relations to define landmark times at which the speech spectrum abruptly changes or reaches an extremum; frames overlapping landmarks have been demonstrated to be sufficient for speech perception. | background 1.00 | 0.05 | 0.05 | asserted 1.00 |
| s3 | In this work, we conduct experiments on the TIMIT corpus, with both GMM and DNN based ASR systems and find that frames containing landmarks are more informative for ASR than others. | result 0.57 | 0.97 | 0.71 | asserted 1.00 |
| s4 | We find that altering the level of emphasis on landmarks by re-weighting acoustic likelihood tends to reduce the phone error rate (PER). | result 1.00 | 0.97 | 0.25 | asserted 0.99 |
| s5 | Furthermore, by leveraging the landmark as a heuristic, one of our hybrid DNN frame dropping strategies maintained a PER within 0.44% of optimal when scoring less than half (45.8% to be precise) of the frames. | result 1.00 | 0.96 | 0.23 | asserted 1.00 |
| s6 | This hybrid strategy out-performs other non-heuristic-based methods and demonstrate the potential of landmarks for reducing computation. | interpretation 0.68 | 0.94 | 0.28 | asserted 0.95 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Most mainstream Automatic Speech Recognition (ASR) systems consider all feature frames equally important. However, acoustic landmark theory is based on a contradictory idea, that some frames are more important than others. Acoustic landmark theory exploits quantal non-linearities in the articulatory-acoustic and acoustic-perceptual relations to define landmark times at which the speech spectrum abruptly changes or reaches an extremum; frames overlapping landmarks have been demonstrated to be sufficient for speech perception. In this work, we conduct experiments on the TIMIT corpus, with both GMM and DNN based ASR systems and find that frames containing landmarks are more informative for ASR than others. We find that altering the level of emphasis on landmarks by re-weighting acoustic likelihood tends to reduce the phone error rate (PER). Furthermore, by leveraging the landmark as a heuristic, one of our hybrid DNN frame dropping strategies maintained a PER within 0.44% of optimal when scoring less than half (45.8% to be precise) of the frames. This hybrid strategy out-performs other non-heuristic-based methods and demonstrate the potential of landmarks for reducing computation.
Human review
How the literature uses it
1 arXiv paper cite this in 2 sentences
Papers citing it · 1 sentence without a confident label
Cites it as background 1 paper
-
Other studies have proposed training two separate sets of classifiers, one trained to recognize landmarks, another trained to recognize steady-state phone segments, and fusing the two for improved accuracy [ref] or for reduced computational complexity [ref] .
Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks · Introduction · 0.85
What it cites · 3 sentences without a confident label
Uses the method or tool of 1 paper
-
This marking procedure is shared by [ref] .
Landmark-based consonant voicing detection on multilingual corpora · Hypotheses · 0.96
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.