Abstract | ||
---|---|---|
Missing data in corrupted audio recordings poses a challenging problem for audio signal processing. In this paper we present an approach that allows us to estimate missing values in the time-frequency domain of audio signals. The proposed approach, based on the Non-negative Hidden Markov Model, enables more temporally coherent estimation for the missing data by taking into account both the spectral and temporal information of the audio signal. This approach is able to reconstruct highly corrupted audio signals with large parts of the spectrogram missing. We demonstrate this approach on real-world polyphonic music signals. The initial experimental results show that our approach has advantages over a previous missing data imputation method. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-28551-6_43 | LVA/ICA |
Keywords | Field | DocType |
non-negative hidden markov model,corrupted audio recording,audio signal processing,audio imputation,missing value,challenging problem,audio signal,missing data,real-world polyphonic music signal,previous missing data | Audio signal,Speech coding,Pattern recognition,Computer science,Spectrogram,Speech recognition,Artificial intelligence,Imputation (statistics),Missing data,Audio signal processing,Hidden Markov model,Missing data imputation | Conference |
Citations | PageRank | References |
8 | 0.53 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jinyu Han | 1 | 69 | 7.92 |
Gautham J. Mysore | 2 | 481 | 34.53 |
Bryan Pardo | 3 | 830 | 63.92 |