1 |
Learning Latent Structures for Cross Action Phrase Relations in Wet Lab Protocols ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Perceptual Loss with Recognition Model for Single-Channel Enhancement and Robust ASR ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Hallucination of speech recognition errors with sequence to sequence learning ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data ...
|
|
|
|
Abstract:
While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback. In particular, phonetic feedback is rare in speech enhancement research even though it includes valuable top-down information. We use the technique of mimic loss to provide phonetic feedback to an off-the-shelf enhancement system, and find gains in objective intelligibility scores on CHiME-4 data. This technique takes a frozen acoustic model trained on clean speech to provide valuable feedback to the enhancement model, even in the case where no parallel speech data is available. Our work is one of the first to show intelligibility improvement for neural enhancement systems without parallel speech data, and we show phonetic feedback can improve a state-of-the-art neural enhancement system trained with parallel speech data. ... : 4 pages + 1 page for references, accepted to ICASSP 2020 ...
|
|
Keyword:
Audio and Speech Processing eess.AS; Computation and Language cs.CL; FOS Computer and information sciences; FOS Electrical engineering, electronic engineering, information engineering; Sound cs.SD
|
|
URL: https://arxiv.org/abs/2003.01769 https://dx.doi.org/10.48550/arxiv.2003.01769
|
|
BASE
|
|
Hide details
|
|
5 |
Ambiguity in medical concept normalization: An analysis of types and coverage in electronic health record datasets
|
|
|
|
In: J Am Med Inform Assoc (2020)
|
|
BASE
|
|
Show details
|
|
6 |
Characterizing the impact of geometric properties of word embeddings on task performance ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Characterizing the impact of geometric properties of word embeddings on task performance
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Spectral feature mapping with mimic loss for robust speech recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Insights into Analogy Completion from the Biomedical Domain ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Gender-Based Language Modeling: Salient Features and Interpolation Methods
|
|
|
|
BASE
|
|
Show details
|
|
|
|