Presentation is loading. Please wait.

Presentation is loading. Please wait.

S. Raghavan,H. P. Greeley, J. Berg, E. Friets, J. PiconeJ. P. Wilson Dept. of ECECreare, Inc., Mississippi State UniversityNew Hampshire Presented by:

Similar presentations


Presentation on theme: "S. Raghavan,H. P. Greeley, J. Berg, E. Friets, J. PiconeJ. P. Wilson Dept. of ECECreare, Inc., Mississippi State UniversityNew Hampshire Presented by:"— Presentation transcript:

1 S. Raghavan,H. P. Greeley, J. Berg, E. Friets, J. PiconeJ. P. Wilson Dept. of ECECreare, Inc., Mississippi State UniversityNew Hampshire Presented by: S. Srinivasan URL: http://www.ece.msstate.edu/research/isip/publications/conferences/ieee_isspit/2006/fatigue_detection/ DETECTING FATIGUE FROM VOICE USING SPEECH RECOGNITION

2 Page 1 of 21 Detecting Fatigue from Voice using Speech Recognition Abstract Goal: To automate the task of fatigue detection using voice. Problem statement: Determine a suitable technique to enable automatic fatigue detection using voice. Also make the system robust to out-of- vocabulary words which directly influence fatigue detection performance. Hypothesis: An LVCSR system can be used for detecting fatigue from voice. Results: Using confidence measures the robustness of the fatigue detection system to out-of-vocabulary words improved by 20%.

3 Page 2 of 21 Detecting Fatigue from Voice using Speech Recognition Motivation Applications of speech recognition have grown from simple speech to text conversion to other more challenging tasks. An ASR system can be used as a core and various applications can be built using the same technology. This work explores the application of speech recognition to the task of fatigue detection from voice. The ISIP ASR toolkit was used as the core speech engine for this work. Speech Recognition Speaker Verification word Spotting Automatic Call routing Automatic Language Detection Automobile Telematics Speech Therapy systems Fatigue Detection Core Speech Engine Focus of this work

4 Page 3 of 21 Detecting Fatigue from Voice using Speech Recognition Signs of Fatigue in Human Speech Creare Inc. provided voice data recorded from subjects who were induced with fatigue by sleep depravation. The spectrograms of a subject before and after fatigue induction is shown below. Non-fatigued speaker saying “papa” Fatigued speaker saying “papa”

5 Page 4 of 21 Detecting Fatigue from Voice using Speech Recognition Changes in Human Voice Production System due to Fatigue From literature it is known that fatigue causes temporal and spectral variations in the speech signal. The spectral variation can be attributed to a change in the human sound production system, while the temporal variation is controlled by the brain and its explanation is beyond the scope of this work. Effects on human sound production system: Yielding walls: The vocal tract walls are not rigid and hence it is known that an increase in the vibration of the walls of the vocal tract causes a slight increase in the lower order formants. Viscosity and thermal loss: It is the friction between air and walls of the vocal tract. This loss causes a slight upward shift on the formant frequencies that exist beyond 3-4 kHz. Lip radiation: For an ideal vocal tract model the lip radiation loss is ignored, but it is known from literature that the lip radiation loss causes a slight decrease in the formants. This effect is more pronounced for higher order formants.

6 Page 5 of 21 Detecting Fatigue from Voice using Speech Recognition Fatigue detection using a Speaker Verification System Speaker Verification: A speaker verification system can be used to model the long term speech characteristics of a speaker. The system builds a model for each individual speaker. Verification is performed by computing a likelihood (likelihood is defined as the conditional probability of the acoustic data given the speaker model). Fatigue detection using the speaker verification system was conducted as follows: 1)Models were trained on data that was collected during the initial stage of the recordings. 2)These models were used for testing. There were six recording stages evenly spread over a duration of thirty six hours.

7 Page 6 of 21 Detecting Fatigue from Voice using Speech Recognition Result from Pilot Speaker verification Experiments Distribution of the likelihood scores of fatigued and non-fatigued speakers Speaker Verification Active Speaker Model Active or fatigued utterance from the speaker Output Observation: No significant difference in the likelihood scores was observed. Input MFCCs One probable reason for poor performance is that not all sounds in human speech are affected by fatigue in the same manner.

8 Page 7 of 21 Detecting Fatigue from Voice using Speech Recognition Effect of Fatigue on Different Phonemes Greeley, et al. found that not all phonemes are affected equally due to fatigue. Certain phonemes showed more variations due to fatigue than others. Certain sounds showed more variations due to fatigue than others

9 Page 8 of 21 Detecting Fatigue from Voice using Speech Recognition Fatigue Detection using a Word Spotter Word Spotting system: A word spotting system determines the presence of words of interest in a speech file. Such a system was built using the ISIP ASR system as follows: 1.Labeled training data was used to train the acoustic models. 2.A garbage model is built by labeling all the words in the transcription by the same token. The garbage model will be used as a substitute for any word other than the keyword in the final hypothesis. 3.The grammar of the recognizer was changed based on what words had to be spotted. Word Spotter Input utterance Loop grammar spotted word alignment Fatigue Detection Measure of fatigue The problem with this system was that it generated a high percentage of false hypothesis and this affected fatigue detection performance.

10 Page 9 of 21 Detecting Fatigue from Voice using Speech Recognition An LVCSR Approach to Detect Fatigue An ASR system trained on the Creare data provided reasonably accurate phonetic alignments. A WER of 11% was obtained. These alignments were used by the fatigue detection software to grab the MFCC vectors corresponding to specific sounds. ASR System Feature Extraction Output Hypothesis Fatigue Detection System Fatigue prediction output Speech signal Advantage of using this approach is that: 1. Unlike speaker verification technique this approach does not require fatigue dependent data for training the ASR system. 2. The grammar of the ASR is fixed unlike the word spotting technique. But the problem of false alarms still exists, especially when there are out-of -vocabulary words, and this problem is tackled by the use of confidence measures.

11 Page 10 of 21 Detecting Fatigue from Voice using Speech Recognition Generating a Baseline ASR System Grammar TypeWER % Sentence level grammar (Fixed phrases)0 Sentence level grammar (Fixed+ Spontaneous phrases) 34 Word level grammar (Fixed phrases)60 Word level grammar (Fixed + Spontaneous phrases) 82 Bigram model (Fixed phrases)52.4 Bigram model (Fixed + Spontaneous phrases)74.5 Grammar tuning experiments on Phase II data using 16-mixture Cross-word triphones Model TypeWER % Word63.9 Monophone54.3 Cross-word triphone47.3 Model selection experiments on FAA data No. of MixturesWER % 147.3 236.3 423.6 811.3 1611.3 Mixture selection experiments on FAA data Phase II data: This data was recorded during a three day military exercise using a PDA (Personal Digital Assistant). The data was very noisy and contained lot of disfluencies. There were 8 fixed phrases and one spontaneous phrase for each of the 21 speakers. FAA data: This consisted of 30 words spoken in a studio environment over a three day period. The speakers read fixed text.

12 Page 11 of 21 Detecting Fatigue from Voice using Speech Recognition Results from state-tying experiments The performance of the system was improved further by tuning the state tying parameters. This was possible since cross-word triphone models were used as the fundamental acoustic model. It was observed that the WER improved by increasing the number of states, but made the model specific to the training data. Hence an optimum value was chosen by observing the WER on open loop experiments. Closed loop state tying experiments Open loop state tying experiments

13 Page 12 of 21 Detecting Fatigue from Voice using Speech Recognition Problem due to False Alarms The output of an ASR system had some errors. The errors are classified as: substitutions, insertions and deletions. The performance of the fatigue prediction system relied on the accuracy of the phonetic alignment. It did not matter if the ASR miss-recognized the required words, but it did matter when there were false alarms. HEAT THE POT INSIDE THE OPEN AND POT FOR FIFTEEN MINUTES. KEEP THE POT INSIDE THE OVEN AND WAIT FOR FIFTEEN MINUTES.Reference Transcription ASR’s Output Not a major problem since it will not be considered for fatigue analysis in any case Correct hypothesis, hence no problem and its alignments will be used for fatigue detection Very serious problem since a totally different MFCC vector set corresponding to the word “wait” will be analyzed assuming it is the word “pot”

14 Page 13 of 21 Detecting Fatigue from Voice using Speech Recognition Using Confidence Measures By using confidence metric we could prune away less likely words that constituted false alarms. The first choice for a confidence metric was the likelihood or the acoustic score of every word in the hypotheses. Observation of the likelihood scores revealed that there was no clear trend that could be useful for pattern classification. An example of such an observation is shown below

15 Page 14 of 21 Detecting Fatigue from Voice using Speech Recognition Word Posteriors as Confidence Measures Word posteriors can be defined as “the sum of the posterior probabilities of all word graph paths of which the word is a part”. Word posteriors can be computed in two ways: 1.N-Best list 2.Word graphs In this work the word posteriors were computed from word graphs as they are much better representation of the search space than N-Best lists. Example of a word graph

16 Page 15 of 21 Detecting Fatigue from Voice using Speech Recognition Computing Word Posteriors from Word Graphs Restating the word posterior definition for clarity: Word posteriors can be defined as “the sum of the posterior probabilities of all word graph paths of which the word is a part”. What does this mean mathematically?

17 Page 16 of 21 Detecting Fatigue from Voice using Speech Recognition Logarithmic word posterior probabilities p=-1.0982 0 2 3 4 5 6 9 10 11 12 8 14 1 p=-0.4051 p=-1.0982 p=-1.0986 p=-0.0086 p=-4.7156 p=-3.604 p=-0.0273 p=-3.6169 p=-0.0459 p=-4.0224 p=-3.6169 p=-0.0459 p=-4.0224 p=-3.2884 p=-0.0459p=-0.0075 Sil This is a test sentence Sil this is the is a the guest quest 13 sentence sense p=-4.8978 p=--4.8978 Sil 7 The ASR system annotates the one-best output with the word posteriors computed from the word graph. These word posteriors are used by the fatigue software to prune away less likely words.

18 Page 17 of 21 Detecting Fatigue from Voice using Speech Recognition Effectiveness of Word Posteriors A clear separation in between the histograms of false word scores and correct word scores was observed. A DET curve was also plotted for both the word likelihood scores and the word posterior scores. It can be observed that the Equal Error Rate is much lower for word posteriors compared to word likelihoods.

19 Page 18 of 21 Detecting Fatigue from Voice using Speech Recognition Applying Confidence Measures to Fatigue Detection The real test for the confidence measure was to test it with the fatigue detection system. The fatigue detection system used the word posteriors corresponding to every word in the one-best output as confidence measures and will prune away less likely words for fatigue detection. The false alarms in the experiment were due to out-of-vocabulary words. The effect of using confidence measures on the test set can be observed from the plot shown below

20 Page 19 of 21 Detecting Fatigue from Voice using Speech Recognition Conclusion and Future Work Conclusion: A suitable mechanism for detecting fatigue using an LVCSR system was developed. A confidence measure algorithm was implemented to make the system robust to false alarms due to out-of-vocabulary words. The confidence measure algorithm helped in improving the performance of the fatigue detection system by 20%. Future Work: A more extensive set of fatigue experiments should be conducted on a larger data set. The data set used for this work was limited by high time and cost of collecting such data sets. The effectiveness of confidence measures can be improved by using a statistical language model instead of a loop grammar.

21 Page 20 of 21 Detecting Fatigue from Voice using Speech Recognition Resources Pattern Recognition Applet: compare popular algorithms on standard or custom data sets Speech Recognition Toolkits: compare SVMs and RVMs to standard approaches using a state of the art ASR toolkit Foundation Classes: generic C++ implementations of many popular statistical modeling approaches

22 Page 21 of 21 Detecting Fatigue from Voice using Speech Recognition References 1.F. Wessel, R. Schlüter, K. Macherey and H. Ney, “Confidence Measures for Large Vocabulary Continuous Speech Recognition,” IEEE Transactions on Speech and Audio Processing, vol. 9, no. 3, pp. 288 ‑ 298, November 2001. 2.G. Evermann and P.C. Woodland, “Large Vocabulary Decoding and Confidence Estimation using Word Posterior Probabilities” Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.8, pp. 2366-2369, Istanbul, Turkey, March 2000. 3.X. Huang, A. Acero, and H.W. Hon, Spoken Language Processing – A Guide to Theory, Algorithm, and System Development, Prentice-Hall, Upper Saddle River, New Jersey, USA, 2001. 4.D. Jurafsky and J.H. Martin, An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice-Hall, Upper Saddle River, New Jersey, USA, 2000. 5.H.P. Greeley, J. Berg, E. Friets, J.P. Wilson, S. Raghavan and J. Picone, “Detecting Fatigue from Voice Using Speech Recognition,” to be presented at the IEEE International Symposium on Signal Processing and Information Technology, Vancouver, Canada, August 2006. 6.S. Raghavan and J. Picone, "Confidence Measures Using Word Posteriors and Word Graphs," IES Spring'05 Seminar Series, January 30, 2005. 7.L. Mangu, E. Brill and A. Stolcke, “Finding Consensus in Speech Recognition: Word Error Minimization and Other Applications of Confusion Networks,” Computer, Speech and Language, vol. 14, no. 4, pp. 373 400, October 2000.


Download ppt "S. Raghavan,H. P. Greeley, J. Berg, E. Friets, J. PiconeJ. P. Wilson Dept. of ECECreare, Inc., Mississippi State UniversityNew Hampshire Presented by:"

Similar presentations


Ads by Google