123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425 |
- functions {
- real confusion_model_lpmf(array[] int group,
- int start, int end,
- int n_classes,
- array[,] int algo,
- array[,] int truth,
- array[] real age,
- array[] real clip_duration,
- array[] matrix lambda//,
- //array[] vector lambda_fp,
- ) {
- real ll = 0;
- vector [4] bp;
- vector[8192] log_contrib_comb;
- int n = size(log_contrib_comb);
- for (k in start:end) {
- for (i in 1:n_classes) {
- log_contrib_comb[:n] = rep_vector(0, n);
- n = 1;
- for (chi in 0:(truth[k,1]>0?max(truth[k,1], algo[k,i]):0)) {
- bp[1] = truth[k,1]==0?0:poisson_lpmf(chi | truth[k,1]*lambda[group[k-start+1],1,i]);
- for (och in 0:(truth[k,2]>0?max(truth[k,2], algo[k,i]-chi):0)) {
- bp[2] = truth[k,2]==0?0:poisson_lpmf(och | truth[k,2]*lambda[group[k-start+1],2,i]);
- for (fem in 0:(truth[k,3]>0?max(truth[k,3], algo[k,i]-chi-och):0)) {
- bp[3] = truth[k,3]==0?0:poisson_lpmf(fem | truth[k,3]*lambda[group[k-start+1],3,i]);
- for (mal in 0:(truth[k,4]>0?max(truth[k,4], algo[k,i]-chi-och-fem):0)) {
- bp[4] = truth[k,4]==0?0:poisson_lpmf(mal | truth[k,4]*lambda[group[k-start+1],4,i]);
- int delta = algo[k,i] - (mal+fem+och+chi);
- // if (delta >= 0) {
- // log_contrib_comb[n] += sum(bp);
- // log_contrib_comb[n] += poisson_lpmf(
- // delta | lambda_fp[group[k-start+1],i]*clip_duration[k]
- // );
- // n = n+1;
- // }
- if (delta==0) {
- log_contrib_comb[n] += sum(bp);
- n = n+1;
- }
- }
- }
- }
- }
- if (n>1) {
- ll += log_sum_exp(log_contrib_comb[1:n-1]);
- }
- }
- }
- return ll;
- }
- real inverse_model_lpmf(array[] int children,
- int start, int end,
- int n_recs,
- int n_classes,
- real duration,
- array [,] int vocs,
- array [] real age,
- matrix truth_vocs,
- array [] matrix actual_confusion,
- //array [] vector actual_fp_rate,
- matrix mus,
- matrix alphas//,
- //vector mus_fp,
- //vector alphas_fp
- ) {
- real ll = 0;
- vector [4] expect;
- for (k in start:end) {
- expect = rep_vector(0, 4);
- for (i in 1:n_classes) {
- ll += gamma_lpdf(actual_confusion[k,i] | alphas[i,:], alphas[i,:]./mus[i,:]);
- //ll += gamma_lpdf(actual_fp_rate[k] | alphas_fp, alphas_fp./mus_fp);
-
- expect[i] = dot_product(truth_vocs[k,:], actual_confusion[k,:,i]);
- //expect[i] += actual_fp_rate[k,i] * duration;
- }
-
- ll += normal_lpdf(vocs[k,:] | expect, sqrt(expect));
- }
- return ll;
- }
- real recs_priors_lpmf(array[] int children,
- int start, int end,
- int n_recs,
- int n_classes,
- real recs_duration,
- array [] real age,
- matrix truth_vocs,
- vector mu_pop_level,
- matrix mu_child_level,
- vector alpha_child_level,
- vector child_dev_age,
- real beta_dev
- ) {
- real ll = 0;
-
- for (k in start:end) {
- real chi_mu = mu_pop_level[1]*exp(
- child_dev_age[children[k-start+1]]*age[k]/12.0/10.0+beta_dev*(mu_child_level[children[k-start+1],2]+mu_child_level[children[k-start+1],3]-mu_pop_level[3]-mu_pop_level[4])*age[k]/12.0/10.0
- );
- ll += gamma_lpdf(
- truth_vocs[k,1]/1000/recs_duration | alpha_child_level[1], alpha_child_level[1]/chi_mu
- );
- ll += gamma_lpdf(
- truth_vocs[k,2:]/1000/recs_duration | alpha_child_level[2:], alpha_child_level[2:]./mu_child_level[children[k-start+1],:]' //'
- );
- }
- return ll;
- }
- }
- // TODO
- // use speech rates to set priors on truth_vocs
- data {
- int<lower=1> n_classes; // number of classes
- // analysis data block
- int<lower=1> n_recs;
- int<lower=1> n_children;
- array[n_recs] int<lower=1> children;
- array[n_recs] real<lower=0> age;
- array[n_recs] int<lower=-1> siblings;
- array[n_recs, n_classes] int<lower=0> vocs_algo1;
- array[n_recs, n_classes] int<lower=0> vocs_algo2;
- array[n_children] int<lower=1> corpus;
- real<lower=0> recs_duration;
- // speaker confusion data block
- int<lower=1> n_clips; // number of clips
- int<lower=1> n_groups; // number of groups
- int<lower=1> n_corpora;
- array [n_clips] int group;
- array [n_clips] int conf_corpus;
- array [n_clips,n_classes] int<lower=0> algo1_total; // algo vocs attributed to specific speakers
- array [n_clips,n_classes] int<lower=0> algo2_total; // algo vocs attributed to specific speakers
- array [n_clips,n_classes] int<lower=0> truth_total;
- array [n_clips] real<lower=0> clip_duration;
- array [n_clips] real<lower=0> clip_age;
- int<lower=0> n_validation;
- // actual speech rates
- int<lower=1> n_rates;
- int<lower=1> n_speech_rate_children;
- array [n_rates,n_classes] int<lower=0> speech_rates;
- array [n_rates] int group_corpus;
- array [n_rates] real<lower=0> durations;
- array [n_rates] real<lower=0> speech_rate_age;
- array [n_rates] int<lower=-1> speech_rate_siblings;
- array [n_rates] int<lower=1,upper=n_speech_rate_children> speech_rate_child;
- // parallel processing
- int<lower=1> threads;
- }
- transformed data {
- vector<lower=0>[n_groups] recording_age;
- array[n_speech_rate_children] int<lower=1> speech_rate_child_corpus;
- array[n_children] int<lower=-1> child_siblings;
- array[n_speech_rate_children] int<lower=-1> speech_rate_child_siblings;
- int no_siblings = 0;
- int has_siblings = 0;
- for (c in 1:n_clips) {
- recording_age[group[c]] = clip_age[c];
- }
- for (k in 1:n_rates) {
- speech_rate_child_corpus[speech_rate_child[k]] = group_corpus[k];
- }
- for (k in 1:n_recs) {
- child_siblings[children[k]] = siblings[k];
- }
- for (c in 1:n_children) {
- if (child_siblings[c] == 0) {
- no_siblings += 1;
- }
- else if (child_siblings[c] > 0) {
- has_siblings += 1;
- }
- }
- for (k in 1:n_rates) {
- speech_rate_child_siblings[speech_rate_child[k]] = speech_rate_siblings[k];
- }
- }
- parameters {
- matrix<lower=0>[n_children,n_classes-1] mu_child_level;
- vector [n_children] child_dev_age;
- matrix<lower=0> [n_recs, n_classes] truth_vocs;
- // nuisance parameters
- array [n_recs] matrix<lower=0>[n_classes,n_classes] actual_confusion_baseline_algo1;
- array [n_recs] matrix<lower=0>[n_classes,n_classes] actual_confusion_baseline_algo2;
- //array [n_recs] vector<lower=0>[n_classes] actual_fp_rate;
- // confusion parameters
- // confusion matrix
- matrix<lower=0>[n_classes,n_classes] alphas_algo1;
- matrix<lower=0>[n_classes,n_classes] mus_algo1;
- array [n_groups] matrix<lower=0>[n_classes,n_classes] lambda_algo1;
- matrix<lower=0>[n_classes,n_classes] alphas_algo2;
- matrix<lower=0>[n_classes,n_classes] mus_algo2;
- array [n_groups] matrix<lower=0>[n_classes,n_classes] lambda_algo2;
- // false positives
- //vector<lower=0>[n_classes] alphas_fp;
- //vector<lower=0>[n_classes] mus_fp;
- //array [n_groups] vector<lower=0>[n_classes] lambda_fp;
- // speech rates
- vector<lower=0>[n_classes] alpha_child_level; // variance across recordings for a given child
- array[2] matrix<lower=0>[n_classes-1,n_corpora] alpha_corpus_level; // variance among children
- matrix<lower=0>[n_classes-1,n_corpora] mu_corpus_level; // child-level average
- vector<lower=0>[n_classes-1] alpha_pop_level; // variance among corpora
- vector<lower=0>[n_classes] mu_pop_level; // population level averages
- vector<lower=0>[n_classes-1] alpha_pop;
- matrix<lower=0>[n_classes,n_rates] speech_rate; // truth speech rates observed in annotated clips
- matrix<lower=0>[n_speech_rate_children,n_classes-1] speech_rate_child_level; // expected speech rate at the child-level
- // siblings
- real beta_sib_och; // effect of having siblings on OCH speech
- real beta_sib_adu; // effect of having siblings on ADU speech
- real<lower=0,upper=1> p_sib; // prob of having siblings
- vector [n_speech_rate_children] child_dev_speech_age;
- // average effect of age
- real alpha_dev;
- real<lower=0> sigma_dev;
- // effect of excess ADU input
- real beta_dev;
- }
- model {
- //actual model
- // inverse confusion model
- target += reduce_sum(
- inverse_model_lpmf, children, 1,
- n_recs, n_classes, recs_duration,
- vocs_algo1, age,
- truth_vocs, actual_confusion_baseline_algo1, mus_algo1, alphas_algo1//, mus_fp, alphas_fp
- );
- target += reduce_sum(
- inverse_model_lpmf, children, 1,
- n_recs, n_classes, recs_duration,
- vocs_algo2, age,
- truth_vocs, actual_confusion_baseline_algo2, mus_algo2, alphas_algo2//, mus_fp, alphas_fp
- );
- // priors on actual speech
- target += reduce_sum(
- recs_priors_lpmf, children, 1,
- n_recs, n_classes, recs_duration, age,
- truth_vocs,
- mu_pop_level, mu_child_level, alpha_child_level,
- child_dev_age, beta_dev
- );
- vector [2] ll;
- int distrib;
- for (c in 1:n_children) {
- // if there is sibling data
- if (child_siblings[c]>=0) {
- distrib = child_siblings[c]>0?2:1;
- mu_child_level[c,1] ~ gamma(
- alpha_corpus_level[distrib,1,corpus[c]],
- (alpha_corpus_level[distrib,1,corpus[c]]/(mu_corpus_level[1,corpus[c]]*exp(
- child_siblings[c]>0?beta_sib_och:0
- )))
- );
- mu_child_level[c,2:] ~ gamma(
- alpha_corpus_level[distrib,2:,corpus[c]],
- (alpha_corpus_level[distrib,2:,corpus[c]]./mu_corpus_level[2:,corpus[c]]*exp(
- child_siblings[c]>0?beta_sib_adu:0
- ))
- );
- }
- // otherwise
- else {
- // assuming no sibling
- ll[1] = log(p_sib)+gamma_lpdf(
- mu_child_level[c,1] | alpha_corpus_level[2,1,corpus[c]], alpha_corpus_level[2,1,corpus[c]]/(mu_corpus_level[1,corpus[c]]*exp(beta_sib_och))
- );
- ll[1] += gamma_lpdf(
- mu_child_level[c,2] | alpha_corpus_level[2,2,corpus[c]], alpha_corpus_level[2,2,corpus[c]]/(mu_corpus_level[2,corpus[c]]*exp(beta_sib_adu))
- );
- ll[1] += gamma_lpdf(
- mu_child_level[c,3] | alpha_corpus_level[2,3,corpus[c]], alpha_corpus_level[2,3,corpus[c]]/(mu_corpus_level[3,corpus[c]]*exp(beta_sib_adu))
- );
- // assuming sibling
- ll[2] = log(1-p_sib)+gamma_lpdf(
- mu_child_level[c,1] | alpha_corpus_level[1,1,corpus[c]], alpha_corpus_level[1,1,corpus[c]]/(mu_corpus_level[1,corpus[c]])
- );
- ll[2] += gamma_lpdf(
- mu_child_level[c,2] | alpha_corpus_level[1,2,corpus[c]], alpha_corpus_level[1,2,corpus[c]]/(mu_corpus_level[2,corpus[c]])
- );
- ll[2] += gamma_lpdf(
- mu_child_level[c,3] | alpha_corpus_level[1,3,corpus[c]], alpha_corpus_level[1,3,corpus[c]]/(mu_corpus_level[3,corpus[c]])
- );
- target += log_sum_exp(ll);
- }
- }
- alpha_child_level ~ gamma(2,1);
- target += reduce_sum(
- confusion_model_lpmf, group, n_clips%/%(threads*4),
- n_classes,
- algo1_total, truth_total, clip_duration, clip_age,
- lambda_algo1//, lambda_fp
- );
- target += reduce_sum(
- confusion_model_lpmf, group, n_clips%/%(threads*4),
- n_classes,
- algo2_total, truth_total, clip_duration, clip_age,
- lambda_algo2//, lambda_fp
- );
- //mus_fp ~ exponential(1);
- //alphas_fp ~ gamma(2, 1);
- for (i in 1:n_classes) {
- //lambda_fp[:,i] ~ gamma(alphas_fp[i], alphas_fp[i]/mus_fp[i]);
- for (j in 1:n_classes) {
- mus_algo1[i,j] ~ exponential(i==j?2:8);
- mus_algo2[i,j] ~ exponential(i==j?2:8);
- alphas_algo1[i,j] ~ gamma(2,1);
- alphas_algo2[i,j] ~ gamma(2,1);
- // mus[i,j] ~ exponential(1);
- // alphas[i,j] ~ exponential(1);
- for (c in 1:n_groups) {
- lambda_algo1[c,i,j] ~ gamma(alphas_algo1[i,j], alphas_algo1[i,j]/mus_algo1[i,j]);
- lambda_algo2[c,i,j] ~ gamma(alphas_algo2[i,j], alphas_algo2[i,j]/mus_algo2[i,j]);
- }
- }
- }
- // speech rates
- mu_pop_level ~ exponential(4); // 250 vocs/hour
- alpha_pop_level ~ gamma(8, 4); // sd = 0.35 x \mu
- alpha_pop ~ gamma(10, 10);
- for (i in 1:n_classes-1) {
- alpha_corpus_level[1,i,:] ~ gamma(4, 4/alpha_pop[i]);
- alpha_corpus_level[2,i,:] ~ gamma(4, 4/alpha_pop[i]);
- mu_corpus_level[i,:] ~ gamma(alpha_pop_level[i],alpha_pop_level[i]/mu_pop_level[i+1]);
- }
- for (g in 1:n_rates) {
- real chi_mu = mu_pop_level[1]*exp(
- child_dev_speech_age[speech_rate_child[g]]*speech_rate_age[g]/12.0/10.0 + beta_dev*(speech_rate_child_level[speech_rate_child[g],2]+speech_rate_child_level[speech_rate_child[g],3]-mu_pop_level[3]-mu_pop_level[4])*speech_rate_age[g]/12.0/10.0
- );
- speech_rate[1,g] ~ gamma(
- alpha_child_level[1],
- alpha_child_level[1]/chi_mu
- );
- speech_rate[2:,g] ~ gamma(
- alpha_child_level[2:],
- (alpha_child_level[2:]./(speech_rate_child_level[speech_rate_child[g],:]')) //'
- );
- speech_rates[g,:] ~ poisson(speech_rate[:,g]*durations[g]*1000);
- }
- for (c in 1:n_speech_rate_children) {
- distrib = child_siblings[c]>0?2:1;
- speech_rate_child_level[c,1] ~ gamma(
- alpha_corpus_level[distrib,1,speech_rate_child_corpus[c]],
- (alpha_corpus_level[distrib,1,speech_rate_child_corpus[c]]/(mu_corpus_level[1,speech_rate_child_corpus[c]]*exp(
- speech_rate_child_siblings[c]>0?beta_sib_och:0
- )))
- );
- speech_rate_child_level[c,2:] ~ gamma(
- alpha_corpus_level[distrib,2:,speech_rate_child_corpus[c]],
- (alpha_corpus_level[distrib,2:,speech_rate_child_corpus[c]]./(mu_corpus_level[2:,speech_rate_child_corpus[c]]*exp(
- speech_rate_child_siblings[c]>0?beta_sib_adu:0
- )))
- );
- }
- child_dev_age ~ normal(alpha_dev, sigma_dev);
- child_dev_speech_age ~ normal(alpha_dev, sigma_dev);
- has_siblings ~ binomial(has_siblings+no_siblings, p_sib);
- p_sib ~ uniform(0, 1);
- beta_sib_och ~ normal(0, 1);
- beta_sib_adu ~ normal(0, 1);
- alpha_dev ~ normal(0, 1);
- sigma_dev ~ exponential(1);
- beta_dev ~ normal(0, 1);
- }
|